{"id":12227,"date":"2026-03-11T13:53:36","date_gmt":"2026-03-11T13:53:36","guid":{"rendered":"https:\/\/meetings.informs.org\/wordpress\/analytics\/?page_id=12227"},"modified":"2026-04-01T16:39:46","modified_gmt":"2026-04-01T16:39:46","slug":"iaaa","status":"publish","type":"page","link":"https:\/\/meetings.informs.org\/wordpress\/analytics\/iaaa\/","title":{"rendered":"IAAA Finalists"},"content":{"rendered":"<!--themify_builder_content-->\n<div id=\"themify_builder_content-12227\" data-postid=\"12227\" class=\"themify_builder_content themify_builder_content-12227 themify_builder tf_clear\">\n                    <div  data-css_id=\"9qsh6\" id=\"homepage-intro\" data-lazy=\"1\" class=\"module_row themify_builder_row fullwidth_row_container tb_9qsh6 tb_first tf_w\">\n                        <div class=\"row_inner col_align_top tb_col_count_1 tf_box tf_rel\">\n                        <div  data-lazy=\"1\" class=\"module_column tb-column col-full tb_beki6 first\">\n                            <div  data-lazy=\"1\" class=\"module_subrow themify_builder_sub_row tf_w col_align_top tb_col_count_1 tb_mrmz6\">\n                <div  data-lazy=\"1\" class=\"module_column sub_column col-full tb_qwqd6 first\">\n                    <!-- module text -->\n<div  class=\"module module-text tb_by5a6   \" data-lazy=\"1\">\n        <div  class=\"tb_text_wrap\">\n        <h1>IAAA Finalists<\/h1>\n<p>The IAAA Finalists will present at the conference on Tuesday, April 14.<\/p>    <\/div>\n<\/div>\n<!-- \/module text -->        <\/div>\n                    <\/div>\n                <\/div>\n                        <\/div>\n        <\/div>\n                        <div  data-lazy=\"1\" class=\"module_row themify_builder_row tb_9oip464 tf_w\">\n                        <div class=\"row_inner col_align_top tb_col_count_2 tf_box tf_rel\">\n                        <div  data-lazy=\"1\" class=\"module_column tb-column col4-2 tb_jwz5464 first\">\n                    <!-- module accordion -->\n<div  class=\"module module-accordion tb_u0bg623 \" data-behavior=\"toggle\" data-lazy=\"1\">\n    \n    <ul class=\"ui module-accordion  embossed tb_default_color\">\n            <li>\n            <div class=\"accordion-title tf_rel\">\n                <a href=\"#acc-u0bg623-0\" class=\"tb_title_accordion\" aria-controls=\"acc-u0bg623-0-content\" aria-expanded=\"false\">\n                    <i class=\"accordion-icon\"><svg  class=\"tf_fa tf-ti-plus\" aria-hidden=\"true\"><use href=\"#tf-ti-plus\"><\/use><\/svg><\/i>                    <i class=\"accordion-active-icon tf_hide\"><svg  class=\"tf_fa tf-ti-minus\" aria-hidden=\"true\"><use href=\"#tf-ti-minus\"><\/use><\/svg><\/i>                    <span class=\"accordion-title-wrap\">AI and Big-Data Brand Intelligence: Sales-Correlated Social Metrics and Market-Valuation Signals<\/span>                <\/a>\n            <\/div><!-- .accordion-title -->\n            <div id=\"acc-u0bg623-0-content\" data-id=\"acc-u0bg623-0\" aria-hidden=\"true\" class=\"accordion-content tf_hide tf_clearfix\">\n                        <div  data-lazy=\"1\" class=\"module_subrow themify_builder_sub_row tf_w col_align_top tb_col_count_1 tb_9el1631\">\n                <div  data-lazy=\"1\" class=\"module_column sub_column tb_735t631 first\">\n                    <!-- module text -->\n<div  class=\"module module-text tb_bq3s631   \" data-lazy=\"1\">\n        <div  class=\"tb_text_wrap\">\n        <p><strong>Prof. Dr. M. Tolga Ak\u00e7ura<\/strong> \u2013 Founder &amp; Chief Scientist, eBrandValue, Inc.; Professor of Marketing, \u00d6zye\u011fin University<\/p>\n<p><strong>Ay\u015fe Ak\u00e7ura<\/strong> \u2013 Founder &amp;\u00a0CEO, eBrandValue, Inc.<\/p>\n<p>We present an end-to-end analytics framework that converts large-scale public social data into sales-correlated metrics, forward-looking forecasts, and capital-market signals. Developed by eBrandValue, Inc., the methodology constructs an author-level interaction graph integrating multi-platform social data with internal sales, pricing, and distribution variables.<\/p>\n<p>Descriptive analytics use embedding-based NLP and large language models to extract topic structures, sentiment dynamics, narrative clusters, and brand-affinity signals. Graph modeling identifies community structures, influence centrality, and diffusion pathways.<\/p>\n<p>Predictive analytics link social-derived features to monthly sales using supervised learning with causality-based lag identification (e.g., Granger). Model selection combines LASSO, stepwise SARIMAX, and neural sequence architectures (e.g., SCINet) within a dynamic ensemble framework. The system produces 12\u201324 month rolling forecasts with uncertainty bands, achieving multi-month-ahead correlations approaching 0.9 and materially improving volume fit relative to legacy brand metrics.<\/p>\n<p>Beyond demand forecasting, we compute brand value measures grounded in consumer-learning theory. Event-study analyses demonstrate that changes in these calculated brand values are statistically significant predictors of abnormal stock-price movements around earnings announcements. Pre-announcement shifts in brand value explain incremental variation in cumulative abnormal returns beyond accounting fundamentals, suggesting that social-derived brand information is partially priced by capital markets.<\/p>\n<p>Prescriptive analytics leverage graph centrality, community detection, and anomaly detection to guide influencer strategy, marketing allocation, and crisis mitigation. The framework integrates econometrics, network science, and machine learning into a scalable, replicable decision-support system deployed across FMCG, financial services, and QSR sectors.<\/p>    <\/div>\n<\/div>\n<!-- \/module text -->        <\/div>\n                    <\/div>\n                    <\/div><!-- .accordion-content -->\n        <\/li>\n            <li>\n            <div class=\"accordion-title tf_rel\">\n                <a href=\"#acc-u0bg623-1\" class=\"tb_title_accordion\" aria-controls=\"acc-u0bg623-1-content\" aria-expanded=\"false\">\n                    <i class=\"accordion-icon\"><svg  class=\"tf_fa tf-ti-plus\" aria-hidden=\"true\"><use href=\"#tf-ti-plus\"><\/use><\/svg><\/i>                    <i class=\"accordion-active-icon tf_hide\"><svg  class=\"tf_fa tf-ti-minus\" aria-hidden=\"true\"><use href=\"#tf-ti-minus\"><\/use><\/svg><\/i>                    <span class=\"accordion-title-wrap\">Designing Novel Adsorbents for removing Naturally Occurring Radioactive Materials (NORMs) from Produced Waters of Oil and Gas Industries, using Computer-Aided Molecular Design<\/span>                <\/a>\n            <\/div><!-- .accordion-title -->\n            <div id=\"acc-u0bg623-1-content\" data-id=\"acc-u0bg623-1\" aria-hidden=\"true\" class=\"accordion-content tf_hide tf_clearfix\">\n                        <div  data-lazy=\"1\" class=\"module_subrow themify_builder_sub_row tf_w col_align_top tb_col_count_1 tb_aov5885\">\n                <div  data-lazy=\"1\" class=\"module_column sub_column tb_sob3885 first\">\n                    <!-- module text -->\n<div  class=\"module module-text tb_4208885   \" data-lazy=\"1\">\n        <div  class=\"tb_text_wrap\">\n        <p><strong>Dr. Urmila Diwekar<\/strong>, Stochastic Research Technologies LLC, USA<\/p>\n<p><strong>Dr. Sanjay Joag<\/strong>, Stochastic Research Technologies LLC, USA<\/p>\n<p><strong>Dr. Daniel Kestering<\/strong>, Stochastic Research Technologies LLC, USA<\/p>\n<p><strong>Dr. Rajib Mukherjee<\/strong>, Stochastic Research Technologies LLC, USA<\/p>\n<p><strong>Mr. Narendra Boppana<\/strong>, Vishwamitra Research Institute, USA<\/p>\n<p>Produced water from oil and gas operations contains Naturally Occurring Radioactive Materials (NORM) and hazardous metals, posing significant environmental and regulatory challenges. This work presents a novel Computer-Aided Molecular Design (CAMD) framework for the systematic design of clay-based adsorbents to efficiently remove NORM and other contaminants. The approach integrates Group Contribution Methods with a combinatorial optimization strategy enhanced by quasi-Monte Carlo sampling, thereby enabling the solution of this large-scale non-convex mixed-integer nonlinear programming problem. The resulting adsorbents demonstrate orders-of-magnitude improvements in removal efficiency and cost-effectiveness compared with existing technologies, while requiring minimal energy and generating low levels of waste. Experimental validation using produced water confirms the predicted performance. The framework is adaptable to site-specific water chemistries and is extended to the selective recovery of critical minerals such as lithium, offering a scalable and economically viable pathway for produced-water treatment and resource recovery.<\/p>    <\/div>\n<\/div>\n<!-- \/module text -->        <\/div>\n                    <\/div>\n                    <\/div><!-- .accordion-content -->\n        <\/li>\n            <li>\n            <div class=\"accordion-title tf_rel\">\n                <a href=\"#acc-u0bg623-2\" class=\"tb_title_accordion\" aria-controls=\"acc-u0bg623-2-content\" aria-expanded=\"false\">\n                    <i class=\"accordion-icon\"><svg  class=\"tf_fa tf-ti-plus\" aria-hidden=\"true\"><use href=\"#tf-ti-plus\"><\/use><\/svg><\/i>                    <i class=\"accordion-active-icon tf_hide\"><svg  class=\"tf_fa tf-ti-minus\" aria-hidden=\"true\"><use href=\"#tf-ti-minus\"><\/use><\/svg><\/i>                    <span class=\"accordion-title-wrap\">Hidden in Plain Sight: Detecting Illicit Massage Businesses from Mobility Patterns<\/span>                <\/a>\n            <\/div><!-- .accordion-title -->\n            <div id=\"acc-u0bg623-2-content\" data-id=\"acc-u0bg623-2\" aria-hidden=\"true\" class=\"accordion-content tf_hide tf_clearfix\">\n                        <div  data-lazy=\"1\" class=\"module_subrow themify_builder_sub_row tf_w col_align_top tb_col_count_1 tb_tyn5954\">\n                <div  data-lazy=\"1\" class=\"module_column sub_column tb_beoh954 first\">\n                    <!-- module text -->\n<div  class=\"module module-text tb_utv2954   \" data-lazy=\"1\">\n        <div  class=\"tb_text_wrap\">\n        <p>From the Institute of Data and Analytics, Culverhouse College of Business, The University of Alabama:<\/p>\n<ul>\n<li><strong>Nick Freeman<\/strong> (freem028@ua.edu)<\/li>\n<li><strong>Roya Shomali<\/strong> (rshomali@crimson.ua.edu)<\/li>\n<li><strong>Greg Bott<\/strong> (gjbott@ua.edu)<\/li>\n<li><strong>Iman Dayarian<\/strong> (idayarian@ua.edu)<\/li>\n<li><strong>Jason Parton<\/strong> (jmparton@ua.edu)<\/li>\n<\/ul>\n<p>From The Network (Arlington, VA):<\/p>\n<ul>\n<li><strong>Louis Wilbrink<\/strong> (louis@thenetworkteam.org)<\/li>\n<li><strong>Jesus Lopez Lugo<\/strong> (lugo@thenetworkteam.org)<\/li>\n<li><strong>Carlos Garcia<\/strong> (carlos@thenetworkteam.org)<\/li>\n<\/ul>\n<p><strong>Abstract<\/strong>: Illicit massage businesses (IMBs) masquerade as legitimate massage parlors while facilitating commercial sex and human trafficking. Traditional detection relies on online review sites, limiting coverage to openly advertised venues. This work develops an analytical methodology using large-scale cell phone mobility data to uncover the &#8220;digital fingerprint&#8221; of IMBs. The approach integrates descriptive, predictive, and prescriptive analytics to transform signals from features such as temporal visitation patterns and dwell times into risk scores that estimate the probability of illicit activity. These risk scores serve as a key input to optimization models that prioritize inspections under budget and capacity constraints.<\/p>    <\/div>\n<\/div>\n<!-- \/module text -->        <\/div>\n                    <\/div>\n                    <\/div><!-- .accordion-content -->\n        <\/li>\n            <li>\n            <div class=\"accordion-title tf_rel\">\n                <a href=\"#acc-u0bg623-3\" class=\"tb_title_accordion\" aria-controls=\"acc-u0bg623-3-content\" aria-expanded=\"false\">\n                    <i class=\"accordion-icon\"><svg  class=\"tf_fa tf-ti-plus\" aria-hidden=\"true\"><use href=\"#tf-ti-plus\"><\/use><\/svg><\/i>                    <i class=\"accordion-active-icon tf_hide\"><svg  class=\"tf_fa tf-ti-minus\" aria-hidden=\"true\"><use href=\"#tf-ti-minus\"><\/use><\/svg><\/i>                    <span class=\"accordion-title-wrap\">Stabilizing Compensation for a Service-Oriented Business<\/span>                <\/a>\n            <\/div><!-- .accordion-title -->\n            <div id=\"acc-u0bg623-3-content\" data-id=\"acc-u0bg623-3\" aria-hidden=\"true\" class=\"accordion-content tf_hide tf_clearfix\">\n                        <div  data-lazy=\"1\" class=\"module_subrow themify_builder_sub_row tf_w col_align_top tb_col_count_1 tb_w3ic413\">\n                <div  data-lazy=\"1\" class=\"module_column sub_column tb_t406413 first\">\n                    <!-- module text -->\n<div  class=\"module module-text tb_zipy413   \" data-lazy=\"1\">\n        <div  class=\"tb_text_wrap\">\n        <p><strong>Kat Tomon Veidmark<\/strong> and <strong>Alexandra Newman<\/strong> \u2013 Colorado School of Mines<\/p>\n<p>Service-oriented businesses rely heavily on labor and expertise, making employee compensation structures central to their financial success. Despite this importance, compensation scales are rarely optimized. The challenge is to design a wage structure that balances business profitability, employee fairness, and competitive pricing.<\/p>\n<p>We develop and apply a mixed-integer nonlinear optimization model to determine a tiered compensation structure. The model (i) ensures the business achieves a desired gross profit per employee, (ii) minimizes deviations in employee wages from the prior compensation scale, and (iii) incorporates an overall service price increase. We then refine the optimized output through managerial adjustments to better align with organizational goals of equity across pay tiers.<\/p>\n<p>Applying the model to data from a service-oriented business in a major metropolitan area, the optimized scale improves average gross profit per commission tier by 29%, while employee wages deviate between &#8211;6% and +4% relative to those earned on the prior scale. To address managerial priorities of equitable pay at lower tiers, adjustments narrow wage deviations to between -4% and +8%, but reduce the average gross profit gain. This trade-off highlights the value of optimization as a decision-support tool, rather than a solution implemented verbatim: the model provides a profit-maximizing baseline, while management can apply equity or retention considerations through targeted modifications. Overall, the approach enables service businesses to strategically balance profitability and employee satisfaction, offering a practical framework for data-driven compensation design.<\/p>    <\/div>\n<\/div>\n<!-- \/module text -->        <\/div>\n                    <\/div>\n                    <\/div><!-- .accordion-content -->\n        <\/li>\n            <li>\n            <div class=\"accordion-title tf_rel\">\n                <a href=\"#acc-u0bg623-4\" class=\"tb_title_accordion\" aria-controls=\"acc-u0bg623-4-content\" aria-expanded=\"false\">\n                    <i class=\"accordion-icon\"><svg  class=\"tf_fa tf-ti-plus\" aria-hidden=\"true\"><use href=\"#tf-ti-plus\"><\/use><\/svg><\/i>                    <i class=\"accordion-active-icon tf_hide\"><svg  class=\"tf_fa tf-ti-minus\" aria-hidden=\"true\"><use href=\"#tf-ti-minus\"><\/use><\/svg><\/i>                    <span class=\"accordion-title-wrap\">Analytics for Better Urban Cycling at the City of Toronto<\/span>                <\/a>\n            <\/div><!-- .accordion-title -->\n            <div id=\"acc-u0bg623-4-content\" data-id=\"acc-u0bg623-4\" aria-hidden=\"true\" class=\"accordion-content tf_hide tf_clearfix\">\n                        <div  data-lazy=\"1\" class=\"module_subrow themify_builder_sub_row tf_w col_align_top tb_col_count_1 tb_hczu955\">\n                <div  data-lazy=\"1\" class=\"module_column sub_column tb_o62b955 first\">\n                    <!-- module text -->\n<div  class=\"module module-text tb_hajo955   \" data-lazy=\"1\">\n        <div  class=\"tb_text_wrap\">\n        <p><strong>Bo Lin<\/strong>, National University of Singapore<\/p>\n<p><strong>Madeleine Bonsma-Fisher<\/strong>, University of Toronto<\/p>\n<p><strong>Shoshanna Saxe<\/strong>, University of Toronto<\/p>\n<p><strong>Timothy Chan<\/strong>, University of Toronto<\/p>\n<p>Cycling is an effective way to promote healthy lifestyles, improve urban mobility, and combat climate change. However, safety and comfort concerns remain major barriers to cycling uptake globally. To make cycling safer and more inviting, we collaborated with the City of Toronto to develop and implement a suite of analytics tools for urban bike infrastructure planning. First, we propose a descriptive analytics framework that assesses cycling stress&#8212;the discomfort cyclists experience&#8212;on each road segment and quantifies the network&#8217;s low-stress cycling accessibility. This framework has been used to evaluate over ten bike infrastructure projects in Toronto and to estimate the infrastructure budget required to meet the city\u2019s net-zero target. Building on this framework, we develop an optimization model that identifies optimal locations for new bike lanes. This model is a large-scale bilevel program that cannot be solved with existing techniques. In response, we develop a machine learning-augmented optimization method that is computationally tractable and can generate provably high-quality solutions. From 2022 to 2024, this approach would have matched the performance of Toronto&#8217;s implemented plan while reducing the required lane length by 25%, saving an estimated 18 million Canadian dollars. As of March 2025, 29.1 km of bike lanes recommended by our model had been approved by Toronto City Council for construction between 2025 and 2027, with an additional 27.6 km under study for future implementation. Finally, we introduce a predictive model and a web application to support broader application of our methods. The predictive model assesses cycling stress based on street-view images, enabling deployment in cities lacking detailed road network data. The web application enables interactive refinement of optimization results, allowing practitioners to engage seamlessly with our tools. As urban centres increasingly prioritize sustainable transportation, this work offers a scalable and user-friendly framework for leveraging analytics to guide impactful infrastructure decisions.<\/p>    <\/div>\n<\/div>\n<!-- \/module text -->        <\/div>\n                    <\/div>\n                    <\/div><!-- .accordion-content -->\n        <\/li>\n            <li>\n            <div class=\"accordion-title tf_rel\">\n                <a href=\"#acc-u0bg623-5\" class=\"tb_title_accordion\" aria-controls=\"acc-u0bg623-5-content\" aria-expanded=\"false\">\n                    <i class=\"accordion-icon\"><svg  class=\"tf_fa tf-ti-plus\" aria-hidden=\"true\"><use href=\"#tf-ti-plus\"><\/use><\/svg><\/i>                    <i class=\"accordion-active-icon tf_hide\"><svg  class=\"tf_fa tf-ti-minus\" aria-hidden=\"true\"><use href=\"#tf-ti-minus\"><\/use><\/svg><\/i>                    <span class=\"accordion-title-wrap\">Hierarchical Spatio-Temporal Uncertainty Quantification for Distributed Energy Adoption<\/span>                <\/a>\n            <\/div><!-- .accordion-title -->\n            <div id=\"acc-u0bg623-5-content\" data-id=\"acc-u0bg623-5\" aria-hidden=\"true\" class=\"accordion-content tf_hide tf_clearfix\">\n                        <div  data-lazy=\"1\" class=\"module_subrow themify_builder_sub_row tf_w col_align_top tb_col_count_1 tb_137p154\">\n                <div  data-lazy=\"1\" class=\"module_column sub_column tb_3y7h154 first\">\n                    <!-- module text -->\n<div  class=\"module module-text tb_mt9o154   \" data-lazy=\"1\">\n        <div  class=\"tb_text_wrap\">\n        <p><strong>Wenbin Zhou<\/strong> (Carnegie Mellon University), <strong>Shixiang Zhu<\/strong> (Carnegie Mellon University), <strong>Feng Qiu<\/strong> (Argonne National Laboratory), <strong>Xuan Wu<\/strong> (Pedernales Electric Cooperative), <strong>Patrick Maguire<\/strong> (AES), <strong>Victoria Cooper<\/strong> (AES), <strong>Ryan Yang<\/strong> (AES)<\/p>\n<p>This work develops methods for forecasting distributed energy resources (DERs) that remain coherent across multiple hierarchical levels of the electric grid while providing rigorous statistical uncertainty guarantees. The methodology integrates descriptive analytics of historical DER adoption patterns, predictive analytics using a multivariate Hawkes process to capture spatial and temporal peer effects and to model future DER adoption trends, and prescriptive analytics that incorporate conformal calibrated uncertainty to support risk-aware capacity planning decisions. The algorithm has been deployed within AES Indiana\u2019s 2025 Integrated Resource Plan (IRP) and will direct DER-related programs impacting over 500,000 customers for the next three years. This work is the first to propose a principled algorithm for coherent uncertainty quantification under aggregation, enabling fine-grained and customized grid planning at different grid hierarchies with robustness guarantees.<\/p>    <\/div>\n<\/div>\n<!-- \/module text -->        <\/div>\n                    <\/div>\n                    <\/div><!-- .accordion-content -->\n        <\/li>\n        <\/ul>\n\n<\/div><!-- \/module accordion -->        <\/div>\n                    <div  data-lazy=\"1\" class=\"module_column tb-column col4-2 tb_dwip619 last\">\n                            <\/div>\n                        <\/div>\n        <\/div>\n        <\/div>\n<!--\/themify_builder_content-->","protected":false},"excerpt":{"rendered":"<p>IAAA Finalists The IAAA Finalists will present at the conference on Tuesday, April 14.<\/p>\n","protected":false},"author":1001140,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_acf_changed":false,"content-type":"","footnotes":""},"class_list":["post-12227","page","type-page","status-publish","hentry","has-post-title","has-post-date","has-post-category","has-post-tag","has-post-comment","has-post-author",""],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v26.0 (Yoast SEO v26.0) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>IAAA Finalists - 2026 INFORMS Analytics+ Conference<\/title>\n<meta name=\"description\" content=\"The IAAA Finalists will present at the 2026 INFORMS Analytics+ Conference.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/meetings.informs.org\/wordpress\/analytics\/iaaa\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"IAAA Finalists - 2026 INFORMS Analytics+ Conference\" \/>\n<meta property=\"og:description\" content=\"The IAAA Finalists will present at the 2026 INFORMS Analytics+ Conference.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/meetings.informs.org\/wordpress\/analytics\/iaaa\/\" \/>\n<meta property=\"og:site_name\" content=\"2026 INFORMS Analytics+ Conference\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/INFORMSpage\/\" \/>\n<meta property=\"article:modified_time\" content=\"2026-04-01T16:39:46+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/meetings.informs.org\/wordpress\/analytics\/files\/2025\/06\/2026_Analytics_Conference_logo_400.png\" \/>\n\t<meta property=\"og:image:width\" content=\"400\" \/>\n\t<meta property=\"og:image:height\" content=\"400\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:site\" content=\"@INFORMS\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/meetings.informs.org\/wordpress\/analytics\/iaaa\/\",\"url\":\"https:\/\/meetings.informs.org\/wordpress\/analytics\/iaaa\/\",\"name\":\"IAAA Finalists - 2026 INFORMS Analytics+ Conference\",\"isPartOf\":{\"@id\":\"https:\/\/meetings.informs.org\/wordpress\/analytics\/#website\"},\"datePublished\":\"2026-03-11T13:53:36+00:00\",\"dateModified\":\"2026-04-01T16:39:46+00:00\",\"description\":\"The IAAA Finalists will present at the 2026 INFORMS Analytics+ Conference.\",\"breadcrumb\":{\"@id\":\"https:\/\/meetings.informs.org\/wordpress\/analytics\/iaaa\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/meetings.informs.org\/wordpress\/analytics\/iaaa\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/meetings.informs.org\/wordpress\/analytics\/iaaa\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/meetings.informs.org\/wordpress\/analytics\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"IAAA Finalists\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/meetings.informs.org\/wordpress\/analytics\/#website\",\"url\":\"https:\/\/meetings.informs.org\/wordpress\/analytics\/\",\"name\":\"2026 INFORMS Analytics+ Conference\",\"description\":\"April 12 \u2013 14\",\"publisher\":{\"@id\":\"https:\/\/meetings.informs.org\/wordpress\/analytics\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/meetings.informs.org\/wordpress\/analytics\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/meetings.informs.org\/wordpress\/analytics\/#organization\",\"name\":\"INFORMS\",\"url\":\"https:\/\/meetings.informs.org\/wordpress\/analytics\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/meetings.informs.org\/wordpress\/analytics\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/meetings.informs.org\/wordpress\/analytics\/files\/2022\/03\/INFORMS_Logo_full_color.jpg\",\"contentUrl\":\"https:\/\/meetings.informs.org\/wordpress\/analytics\/files\/2022\/03\/INFORMS_Logo_full_color.jpg\",\"width\":300,\"height\":72,\"caption\":\"INFORMS\"},\"image\":{\"@id\":\"https:\/\/meetings.informs.org\/wordpress\/analytics\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/INFORMSpage\/\",\"https:\/\/x.com\/INFORMS\",\"http:\/\/instagram.com\/informs_orms\",\"https:\/\/www.linkedin.com\/groups\/82644\/profile\",\"https:\/\/www.pinterest.com\/informs\/_saved\/\",\"https:\/\/www.youtube.com\/user\/INFORMSonline\",\"https:\/\/en.wikipedia.org\/wiki\/Institute_for_Operations_Research_and_the_Management_Sciences\"]}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"IAAA Finalists - 2026 INFORMS Analytics+ Conference","description":"The IAAA Finalists will present at the 2026 INFORMS Analytics+ Conference.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/meetings.informs.org\/wordpress\/analytics\/iaaa\/","og_locale":"en_US","og_type":"article","og_title":"IAAA Finalists - 2026 INFORMS Analytics+ Conference","og_description":"The IAAA Finalists will present at the 2026 INFORMS Analytics+ Conference.","og_url":"https:\/\/meetings.informs.org\/wordpress\/analytics\/iaaa\/","og_site_name":"2026 INFORMS Analytics+ Conference","article_publisher":"https:\/\/www.facebook.com\/INFORMSpage\/","article_modified_time":"2026-04-01T16:39:46+00:00","og_image":[{"width":400,"height":400,"url":"https:\/\/meetings.informs.org\/wordpress\/analytics\/files\/2025\/06\/2026_Analytics_Conference_logo_400.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_site":"@INFORMS","schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/meetings.informs.org\/wordpress\/analytics\/iaaa\/","url":"https:\/\/meetings.informs.org\/wordpress\/analytics\/iaaa\/","name":"IAAA Finalists - 2026 INFORMS Analytics+ Conference","isPartOf":{"@id":"https:\/\/meetings.informs.org\/wordpress\/analytics\/#website"},"datePublished":"2026-03-11T13:53:36+00:00","dateModified":"2026-04-01T16:39:46+00:00","description":"The IAAA Finalists will present at the 2026 INFORMS Analytics+ Conference.","breadcrumb":{"@id":"https:\/\/meetings.informs.org\/wordpress\/analytics\/iaaa\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/meetings.informs.org\/wordpress\/analytics\/iaaa\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/meetings.informs.org\/wordpress\/analytics\/iaaa\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/meetings.informs.org\/wordpress\/analytics\/"},{"@type":"ListItem","position":2,"name":"IAAA Finalists"}]},{"@type":"WebSite","@id":"https:\/\/meetings.informs.org\/wordpress\/analytics\/#website","url":"https:\/\/meetings.informs.org\/wordpress\/analytics\/","name":"2026 INFORMS Analytics+ Conference","description":"April 12 \u2013 14","publisher":{"@id":"https:\/\/meetings.informs.org\/wordpress\/analytics\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/meetings.informs.org\/wordpress\/analytics\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/meetings.informs.org\/wordpress\/analytics\/#organization","name":"INFORMS","url":"https:\/\/meetings.informs.org\/wordpress\/analytics\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/meetings.informs.org\/wordpress\/analytics\/#\/schema\/logo\/image\/","url":"https:\/\/meetings.informs.org\/wordpress\/analytics\/files\/2022\/03\/INFORMS_Logo_full_color.jpg","contentUrl":"https:\/\/meetings.informs.org\/wordpress\/analytics\/files\/2022\/03\/INFORMS_Logo_full_color.jpg","width":300,"height":72,"caption":"INFORMS"},"image":{"@id":"https:\/\/meetings.informs.org\/wordpress\/analytics\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/INFORMSpage\/","https:\/\/x.com\/INFORMS","http:\/\/instagram.com\/informs_orms","https:\/\/www.linkedin.com\/groups\/82644\/profile","https:\/\/www.pinterest.com\/informs\/_saved\/","https:\/\/www.youtube.com\/user\/INFORMSonline","https:\/\/en.wikipedia.org\/wiki\/Institute_for_Operations_Research_and_the_Management_Sciences"]}]}},"builder_content":"<h1>IAAA Finalists<\/h1> <p>The IAAA Finalists will present at the conference on Tuesday, April 14.<\/p>\n<ul><li><h4>AI and Big-Data Brand Intelligence: Sales-Correlated Social Metrics and Market-Valuation Signals<\/h4><p><strong>Prof. Dr. M. Tolga Ak\u00e7ura<\/strong> \u2013 Founder &amp; Chief Scientist, eBrandValue, Inc.; Professor of Marketing, \u00d6zye\u011fin University<\/p> <p><strong>Ay\u015fe Ak\u00e7ura<\/strong> \u2013 Founder &amp;\u00a0CEO, eBrandValue, Inc.<\/p> <p>We present an end-to-end analytics framework that converts large-scale public social data into sales-correlated metrics, forward-looking forecasts, and capital-market signals. Developed by eBrandValue, Inc., the methodology constructs an author-level interaction graph integrating multi-platform social data with internal sales, pricing, and distribution variables.<\/p> <p>Descriptive analytics use embedding-based NLP and large language models to extract topic structures, sentiment dynamics, narrative clusters, and brand-affinity signals. Graph modeling identifies community structures, influence centrality, and diffusion pathways.<\/p> <p>Predictive analytics link social-derived features to monthly sales using supervised learning with causality-based lag identification (e.g., Granger). Model selection combines LASSO, stepwise SARIMAX, and neural sequence architectures (e.g., SCINet) within a dynamic ensemble framework. The system produces 12\u201324 month rolling forecasts with uncertainty bands, achieving multi-month-ahead correlations approaching 0.9 and materially improving volume fit relative to legacy brand metrics.<\/p> <p>Beyond demand forecasting, we compute brand value measures grounded in consumer-learning theory. Event-study analyses demonstrate that changes in these calculated brand values are statistically significant predictors of abnormal stock-price movements around earnings announcements. Pre-announcement shifts in brand value explain incremental variation in cumulative abnormal returns beyond accounting fundamentals, suggesting that social-derived brand information is partially priced by capital markets.<\/p> <p>Prescriptive analytics leverage graph centrality, community detection, and anomaly detection to guide influencer strategy, marketing allocation, and crisis mitigation. The framework integrates econometrics, network science, and machine learning into a scalable, replicable decision-support system deployed across FMCG, financial services, and QSR sectors.<\/p><\/li><li><h4>Designing Novel Adsorbents for removing Naturally Occurring Radioactive Materials (NORMs) from Produced Waters of Oil and Gas Industries, using Computer-Aided Molecular Design<\/h4><p><strong>Dr. Urmila Diwekar<\/strong>, Stochastic Research Technologies LLC, USA<\/p> <p><strong>Dr. Sanjay Joag<\/strong>, Stochastic Research Technologies LLC, USA<\/p> <p><strong>Dr. Daniel Kestering<\/strong>, Stochastic Research Technologies LLC, USA<\/p> <p><strong>Dr. Rajib Mukherjee<\/strong>, Stochastic Research Technologies LLC, USA<\/p> <p><strong>Mr. Narendra Boppana<\/strong>, Vishwamitra Research Institute, USA<\/p> <p>Produced water from oil and gas operations contains Naturally Occurring Radioactive Materials (NORM) and hazardous metals, posing significant environmental and regulatory challenges. This work presents a novel Computer-Aided Molecular Design (CAMD) framework for the systematic design of clay-based adsorbents to efficiently remove NORM and other contaminants. The approach integrates Group Contribution Methods with a combinatorial optimization strategy enhanced by quasi-Monte Carlo sampling, thereby enabling the solution of this large-scale non-convex mixed-integer nonlinear programming problem. The resulting adsorbents demonstrate orders-of-magnitude improvements in removal efficiency and cost-effectiveness compared with existing technologies, while requiring minimal energy and generating low levels of waste. Experimental validation using produced water confirms the predicted performance. The framework is adaptable to site-specific water chemistries and is extended to the selective recovery of critical minerals such as lithium, offering a scalable and economically viable pathway for produced-water treatment and resource recovery.<\/p><\/li><li><h4>Hidden in Plain Sight: Detecting Illicit Massage Businesses from Mobility Patterns<\/h4><p>From the Institute of Data and Analytics, Culverhouse College of Business, The University of Alabama:<\/p> <ul> <li><strong>Nick Freeman<\/strong> (freem028@ua.edu)<\/li> <li><strong>Roya Shomali<\/strong> (rshomali@crimson.ua.edu)<\/li> <li><strong>Greg Bott<\/strong> (gjbott@ua.edu)<\/li> <li><strong>Iman Dayarian<\/strong> (idayarian@ua.edu)<\/li> <li><strong>Jason Parton<\/strong> (jmparton@ua.edu)<\/li> <\/ul> <p>From The Network (Arlington, VA):<\/p> <ul> <li><strong>Louis Wilbrink<\/strong> (louis@thenetworkteam.org)<\/li> <li><strong>Jesus Lopez Lugo<\/strong> (lugo@thenetworkteam.org)<\/li> <li><strong>Carlos Garcia<\/strong> (carlos@thenetworkteam.org)<\/li> <\/ul> <p><strong>Abstract<\/strong>: Illicit massage businesses (IMBs) masquerade as legitimate massage parlors while facilitating commercial sex and human trafficking. Traditional detection relies on online review sites, limiting coverage to openly advertised venues. This work develops an analytical methodology using large-scale cell phone mobility data to uncover the \"digital fingerprint\" of IMBs. The approach integrates descriptive, predictive, and prescriptive analytics to transform signals from features such as temporal visitation patterns and dwell times into risk scores that estimate the probability of illicit activity. These risk scores serve as a key input to optimization models that prioritize inspections under budget and capacity constraints.<\/p><\/li><li><h4>Stabilizing Compensation for a Service-Oriented Business<\/h4><p><strong>Kat Tomon Veidmark<\/strong> and <strong>Alexandra Newman<\/strong> \u2013 Colorado School of Mines<\/p> <p>Service-oriented businesses rely heavily on labor and expertise, making employee compensation structures central to their financial success. Despite this importance, compensation scales are rarely optimized. The challenge is to design a wage structure that balances business profitability, employee fairness, and competitive pricing.<\/p> <p>We develop and apply a mixed-integer nonlinear optimization model to determine a tiered compensation structure. The model (i) ensures the business achieves a desired gross profit per employee, (ii) minimizes deviations in employee wages from the prior compensation scale, and (iii) incorporates an overall service price increase. We then refine the optimized output through managerial adjustments to better align with organizational goals of equity across pay tiers.<\/p> <p>Applying the model to data from a service-oriented business in a major metropolitan area, the optimized scale improves average gross profit per commission tier by 29%, while employee wages deviate between --6% and +4% relative to those earned on the prior scale. To address managerial priorities of equitable pay at lower tiers, adjustments narrow wage deviations to between -4% and +8%, but reduce the average gross profit gain. This trade-off highlights the value of optimization as a decision-support tool, rather than a solution implemented verbatim: the model provides a profit-maximizing baseline, while management can apply equity or retention considerations through targeted modifications. Overall, the approach enables service businesses to strategically balance profitability and employee satisfaction, offering a practical framework for data-driven compensation design.<\/p><\/li><li><h4>Analytics for Better Urban Cycling at the City of Toronto<\/h4><p><strong>Bo Lin<\/strong>, National University of Singapore<\/p> <p><strong>Madeleine Bonsma-Fisher<\/strong>, University of Toronto<\/p> <p><strong>Shoshanna Saxe<\/strong>, University of Toronto<\/p> <p><strong>Timothy Chan<\/strong>, University of Toronto<\/p> <p>Cycling is an effective way to promote healthy lifestyles, improve urban mobility, and combat climate change. However, safety and comfort concerns remain major barriers to cycling uptake globally. To make cycling safer and more inviting, we collaborated with the City of Toronto to develop and implement a suite of analytics tools for urban bike infrastructure planning. First, we propose a descriptive analytics framework that assesses cycling stress---the discomfort cyclists experience---on each road segment and quantifies the network's low-stress cycling accessibility. This framework has been used to evaluate over ten bike infrastructure projects in Toronto and to estimate the infrastructure budget required to meet the city\u2019s net-zero target. Building on this framework, we develop an optimization model that identifies optimal locations for new bike lanes. This model is a large-scale bilevel program that cannot be solved with existing techniques. In response, we develop a machine learning-augmented optimization method that is computationally tractable and can generate provably high-quality solutions. From 2022 to 2024, this approach would have matched the performance of Toronto's implemented plan while reducing the required lane length by 25%, saving an estimated 18 million Canadian dollars. As of March 2025, 29.1 km of bike lanes recommended by our model had been approved by Toronto City Council for construction between 2025 and 2027, with an additional 27.6 km under study for future implementation. Finally, we introduce a predictive model and a web application to support broader application of our methods. The predictive model assesses cycling stress based on street-view images, enabling deployment in cities lacking detailed road network data. The web application enables interactive refinement of optimization results, allowing practitioners to engage seamlessly with our tools. As urban centres increasingly prioritize sustainable transportation, this work offers a scalable and user-friendly framework for leveraging analytics to guide impactful infrastructure decisions.<\/p><\/li><li><h4>Hierarchical Spatio-Temporal Uncertainty Quantification for Distributed Energy Adoption<\/h4><p><strong>Wenbin Zhou<\/strong> (Carnegie Mellon University), <strong>Shixiang Zhu<\/strong> (Carnegie Mellon University), <strong>Feng Qiu<\/strong> (Argonne National Laboratory), <strong>Xuan Wu<\/strong> (Pedernales Electric Cooperative), <strong>Patrick Maguire<\/strong> (AES), <strong>Victoria Cooper<\/strong> (AES), <strong>Ryan Yang<\/strong> (AES)<\/p> <p>This work develops methods for forecasting distributed energy resources (DERs) that remain coherent across multiple hierarchical levels of the electric grid while providing rigorous statistical uncertainty guarantees. The methodology integrates descriptive analytics of historical DER adoption patterns, predictive analytics using a multivariate Hawkes process to capture spatial and temporal peer effects and to model future DER adoption trends, and prescriptive analytics that incorporate conformal calibrated uncertainty to support risk-aware capacity planning decisions. The algorithm has been deployed within AES Indiana\u2019s 2025 Integrated Resource Plan (IRP) and will direct DER-related programs impacting over 500,000 customers for the next three years. This work is the first to propose a principled algorithm for coherent uncertainty quantification under aggregation, enabling fine-grained and customized grid planning at different grid hierarchies with robustness guarantees.<\/p><\/li><\/ul>\n<p><strong>Prof. Dr. M. Tolga Ak\u00e7ura<\/strong> \u2013 Founder &amp; Chief Scientist, eBrandValue, Inc.; Professor of Marketing, \u00d6zye\u011fin University<\/p> <p><strong>Ay\u015fe Ak\u00e7ura<\/strong> \u2013 Founder &amp;\u00a0CEO, eBrandValue, Inc.<\/p> <p>We present an end-to-end analytics framework that converts large-scale public social data into sales-correlated metrics, forward-looking forecasts, and capital-market signals. Developed by eBrandValue, Inc., the methodology constructs an author-level interaction graph integrating multi-platform social data with internal sales, pricing, and distribution variables.<\/p> <p>Descriptive analytics use embedding-based NLP and large language models to extract topic structures, sentiment dynamics, narrative clusters, and brand-affinity signals. Graph modeling identifies community structures, influence centrality, and diffusion pathways.<\/p> <p>Predictive analytics link social-derived features to monthly sales using supervised learning with causality-based lag identification (e.g., Granger). Model selection combines LASSO, stepwise SARIMAX, and neural sequence architectures (e.g., SCINet) within a dynamic ensemble framework. The system produces 12\u201324 month rolling forecasts with uncertainty bands, achieving multi-month-ahead correlations approaching 0.9 and materially improving volume fit relative to legacy brand metrics.<\/p> <p>Beyond demand forecasting, we compute brand value measures grounded in consumer-learning theory. Event-study analyses demonstrate that changes in these calculated brand values are statistically significant predictors of abnormal stock-price movements around earnings announcements. Pre-announcement shifts in brand value explain incremental variation in cumulative abnormal returns beyond accounting fundamentals, suggesting that social-derived brand information is partially priced by capital markets.<\/p> <p>Prescriptive analytics leverage graph centrality, community detection, and anomaly detection to guide influencer strategy, marketing allocation, and crisis mitigation. The framework integrates econometrics, network science, and machine learning into a scalable, replicable decision-support system deployed across FMCG, financial services, and QSR sectors.<\/p>\n<p><strong>Dr. Urmila Diwekar<\/strong>, Stochastic Research Technologies LLC, USA<\/p> <p><strong>Dr. Sanjay Joag<\/strong>, Stochastic Research Technologies LLC, USA<\/p> <p><strong>Dr. Daniel Kestering<\/strong>, Stochastic Research Technologies LLC, USA<\/p> <p><strong>Dr. Rajib Mukherjee<\/strong>, Stochastic Research Technologies LLC, USA<\/p> <p><strong>Mr. Narendra Boppana<\/strong>, Vishwamitra Research Institute, USA<\/p> <p>Produced water from oil and gas operations contains Naturally Occurring Radioactive Materials (NORM) and hazardous metals, posing significant environmental and regulatory challenges. This work presents a novel Computer-Aided Molecular Design (CAMD) framework for the systematic design of clay-based adsorbents to efficiently remove NORM and other contaminants. The approach integrates Group Contribution Methods with a combinatorial optimization strategy enhanced by quasi-Monte Carlo sampling, thereby enabling the solution of this large-scale non-convex mixed-integer nonlinear programming problem. The resulting adsorbents demonstrate orders-of-magnitude improvements in removal efficiency and cost-effectiveness compared with existing technologies, while requiring minimal energy and generating low levels of waste. Experimental validation using produced water confirms the predicted performance. The framework is adaptable to site-specific water chemistries and is extended to the selective recovery of critical minerals such as lithium, offering a scalable and economically viable pathway for produced-water treatment and resource recovery.<\/p>\n<p>From the Institute of Data and Analytics, Culverhouse College of Business, The University of Alabama:<\/p> <ul> <li><strong>Nick Freeman<\/strong> (freem028@ua.edu)<\/li> <li><strong>Roya Shomali<\/strong> (rshomali@crimson.ua.edu)<\/li> <li><strong>Greg Bott<\/strong> (gjbott@ua.edu)<\/li> <li><strong>Iman Dayarian<\/strong> (idayarian@ua.edu)<\/li> <li><strong>Jason Parton<\/strong> (jmparton@ua.edu)<\/li> <\/ul> <p>From The Network (Arlington, VA):<\/p> <ul> <li><strong>Louis Wilbrink<\/strong> (louis@thenetworkteam.org)<\/li> <li><strong>Jesus Lopez Lugo<\/strong> (lugo@thenetworkteam.org)<\/li> <li><strong>Carlos Garcia<\/strong> (carlos@thenetworkteam.org)<\/li> <\/ul> <p><strong>Abstract<\/strong>: Illicit massage businesses (IMBs) masquerade as legitimate massage parlors while facilitating commercial sex and human trafficking. Traditional detection relies on online review sites, limiting coverage to openly advertised venues. This work develops an analytical methodology using large-scale cell phone mobility data to uncover the \"digital fingerprint\" of IMBs. The approach integrates descriptive, predictive, and prescriptive analytics to transform signals from features such as temporal visitation patterns and dwell times into risk scores that estimate the probability of illicit activity. These risk scores serve as a key input to optimization models that prioritize inspections under budget and capacity constraints.<\/p>\n<p><strong>Kat Tomon Veidmark<\/strong> and <strong>Alexandra Newman<\/strong> \u2013 Colorado School of Mines<\/p> <p>Service-oriented businesses rely heavily on labor and expertise, making employee compensation structures central to their financial success. Despite this importance, compensation scales are rarely optimized. The challenge is to design a wage structure that balances business profitability, employee fairness, and competitive pricing.<\/p> <p>We develop and apply a mixed-integer nonlinear optimization model to determine a tiered compensation structure. The model (i) ensures the business achieves a desired gross profit per employee, (ii) minimizes deviations in employee wages from the prior compensation scale, and (iii) incorporates an overall service price increase. We then refine the optimized output through managerial adjustments to better align with organizational goals of equity across pay tiers.<\/p> <p>Applying the model to data from a service-oriented business in a major metropolitan area, the optimized scale improves average gross profit per commission tier by 29%, while employee wages deviate between --6% and +4% relative to those earned on the prior scale. To address managerial priorities of equitable pay at lower tiers, adjustments narrow wage deviations to between -4% and +8%, but reduce the average gross profit gain. This trade-off highlights the value of optimization as a decision-support tool, rather than a solution implemented verbatim: the model provides a profit-maximizing baseline, while management can apply equity or retention considerations through targeted modifications. Overall, the approach enables service businesses to strategically balance profitability and employee satisfaction, offering a practical framework for data-driven compensation design.<\/p>\n<p><strong>Bo Lin<\/strong>, National University of Singapore<\/p> <p><strong>Madeleine Bonsma-Fisher<\/strong>, University of Toronto<\/p> <p><strong>Shoshanna Saxe<\/strong>, University of Toronto<\/p> <p><strong>Timothy Chan<\/strong>, University of Toronto<\/p> <p>Cycling is an effective way to promote healthy lifestyles, improve urban mobility, and combat climate change. However, safety and comfort concerns remain major barriers to cycling uptake globally. To make cycling safer and more inviting, we collaborated with the City of Toronto to develop and implement a suite of analytics tools for urban bike infrastructure planning. First, we propose a descriptive analytics framework that assesses cycling stress---the discomfort cyclists experience---on each road segment and quantifies the network's low-stress cycling accessibility. This framework has been used to evaluate over ten bike infrastructure projects in Toronto and to estimate the infrastructure budget required to meet the city\u2019s net-zero target. Building on this framework, we develop an optimization model that identifies optimal locations for new bike lanes. This model is a large-scale bilevel program that cannot be solved with existing techniques. In response, we develop a machine learning-augmented optimization method that is computationally tractable and can generate provably high-quality solutions. From 2022 to 2024, this approach would have matched the performance of Toronto's implemented plan while reducing the required lane length by 25%, saving an estimated 18 million Canadian dollars. As of March 2025, 29.1 km of bike lanes recommended by our model had been approved by Toronto City Council for construction between 2025 and 2027, with an additional 27.6 km under study for future implementation. Finally, we introduce a predictive model and a web application to support broader application of our methods. The predictive model assesses cycling stress based on street-view images, enabling deployment in cities lacking detailed road network data. The web application enables interactive refinement of optimization results, allowing practitioners to engage seamlessly with our tools. As urban centres increasingly prioritize sustainable transportation, this work offers a scalable and user-friendly framework for leveraging analytics to guide impactful infrastructure decisions.<\/p>\n<p><strong>Wenbin Zhou<\/strong> (Carnegie Mellon University), <strong>Shixiang Zhu<\/strong> (Carnegie Mellon University), <strong>Feng Qiu<\/strong> (Argonne National Laboratory), <strong>Xuan Wu<\/strong> (Pedernales Electric Cooperative), <strong>Patrick Maguire<\/strong> (AES), <strong>Victoria Cooper<\/strong> (AES), <strong>Ryan Yang<\/strong> (AES)<\/p> <p>This work develops methods for forecasting distributed energy resources (DERs) that remain coherent across multiple hierarchical levels of the electric grid while providing rigorous statistical uncertainty guarantees. The methodology integrates descriptive analytics of historical DER adoption patterns, predictive analytics using a multivariate Hawkes process to capture spatial and temporal peer effects and to model future DER adoption trends, and prescriptive analytics that incorporate conformal calibrated uncertainty to support risk-aware capacity planning decisions. The algorithm has been deployed within AES Indiana\u2019s 2025 Integrated Resource Plan (IRP) and will direct DER-related programs impacting over 500,000 customers for the next three years. This work is the first to propose a principled algorithm for coherent uncertainty quantification under aggregation, enabling fine-grained and customized grid planning at different grid hierarchies with robustness guarantees.<\/p>","_links":{"self":[{"href":"https:\/\/meetings.informs.org\/wordpress\/analytics\/wp-json\/wp\/v2\/pages\/12227","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/meetings.informs.org\/wordpress\/analytics\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/meetings.informs.org\/wordpress\/analytics\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/meetings.informs.org\/wordpress\/analytics\/wp-json\/wp\/v2\/users\/1001140"}],"replies":[{"embeddable":true,"href":"https:\/\/meetings.informs.org\/wordpress\/analytics\/wp-json\/wp\/v2\/comments?post=12227"}],"version-history":[{"count":8,"href":"https:\/\/meetings.informs.org\/wordpress\/analytics\/wp-json\/wp\/v2\/pages\/12227\/revisions"}],"predecessor-version":[{"id":12771,"href":"https:\/\/meetings.informs.org\/wordpress\/analytics\/wp-json\/wp\/v2\/pages\/12227\/revisions\/12771"}],"wp:attachment":[{"href":"https:\/\/meetings.informs.org\/wordpress\/analytics\/wp-json\/wp\/v2\/media?parent=12227"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}