INFORMS Prizes & Special Sessions

INFORMS grants several prestigious Institute-wide prizes and awards for meritorious achievement each year. This track will feature presentations for the Wagner Prize, INFORMS Prize, and the UPS George D. Smith Prize winner. Innovative Applications in Analytics Award (IAAA) finalists will also present. Special sessions include presentations hosted by our Certified Analytics Professional (CAP^®) Program and Women in OR/MS.

2022 Daniel H. Wagner Prize Reprise: Generalized Synthetic Control for TestOps at ABl: Models, Algorithms, and Infrastructure

Speakers: Tianyi Peng, MIT and Iva Rosa Montenegro, Anheuser-Busch InBev

Click to view abstract

In this presentation they describe a novel approach to learning from experiments in the world of physical retail, and an associated platform, TestOps, implemented by ABI and MIT. TestOps leverages a recent theoretical breakthrough to learn from experiments when treatment effects are small, the environment is noisy and non-stationary, and adherence problems are commonplace, resulting in ~100x increase of experimental power relative to alternatives. TestOps currently runs experiments impacting ~135M USD in revenue every month and routinely identifies interventions that result in a 1-2% increase in sales volume.

INFORMS Advocacy Initiative: Promoting Data-Driven Decision Making in Washington, DC

Speaker: Jeff Cohen, Chief Strategy & Innovation Officer at INFORMS

Executive

Filling Your Cup: What it Takes to Be an Effective Leader (Hosted by Women in OR/MS)

Speaker: Janice Lichtenwaldt, Executive Leadership Coach at Virago Coaching

Executive

Innovative Applications in Analytics Award (IAAA)

The IAAA Finalists will present at the conference on Tuesday, April 18 in the INFORMS Prizes & Special Sessions Track from 9:10 – 11:55am EST. Judges will then review the rank and announce the winner at the INFORMS Analytics Society luncheon.

An Integrated Deep Learning and Online Optimization Approach to Assign the Fulfillment Routes to Parcels

Cainiao Network, a logistics arm of the Alibaba Group, collaborates with logistics partners to provide delivery services. For a sequence of randomly created parcels within a period (e.g., one day), we need to make decisions sequentially and select a series of fulfillment routes with minimal costs while satisfying the constraints (e.g., the limited number of orders that a partner can assign). For this online decision problem, we first design a forecasting algorithm based on deep learning to predict the number of parcels created in the period. Then, taking the number as input, we employ an online algorithm based on the optimality condition to make real-time decisions. Since April 2021, the approach has been implemented for parcels from China to other countries, thus saving millions of dollars annually.

From Particulate processes to In-vitro Fertilization: Theory to Clinical Practice

The success of In-vitro fertilization (IVF) majorly depends upon successful superovulation, defined by the number and uniformly high quality of eggs retrieved in a cycle. Currently, this step is executed using almost daily monitoring of the follicular development using ultrasound and blood tests. Although there are general guidelines for the dosage, the dose is not optimized for each patient, and overstimulation complications can occur. The cost of testing and drugs makes this stage very expensive. To overcome the shortcoming of this system, we have developed a mathematical procedure that can provide a personalized model and optimal drug treatment for each patient. Recently, we conducted clinical trials in India. The results show that the dosage predicted by using the model is 30-40% less than that suggested by the IVF doctors. The testing for patients is reduced by 72%. We also found that the number of good-quality embryos obtained using this approach was significantly higher than in current practice. This model and optimal control procedure were released in early September as a decision support tool Opt-IVF for hospitals to use in their clinical practice. So far, five hospitals have signed up to use (and are using it daily).

Instrumenting While Experimenting: An Empirical Method for Competitive Pricing at Scale

We partner with a leading U.S. e-commerce retailer and develop a competitive pricing method in the context of increasing competition in online retailing. Our method allows retailers to more accurately respond to competitors’ price changes at scale. First, we construct a parsimonious demand model that captures the key trade-off in competitive pricing by accounting for two types of customers heterogeneous in their “price-shopping”’ behavior. Next, we design and implement a large-scale randomized price experiment on over 10,000 products. Leveraging the experiment as well as the control function approach, we are able to obtain unbiased estimates of the demand model, in particular, price elasticities of both loyal and price-shopping consumers as well as the sales lift when we undercut competitors in price. Lastly, we recommend price responses by solving a constrained optimization problem which uses the estimated demand model as an input. We test this pricing method through another large-scale controlled field experiment on over 10,000 products and demonstrate significant improvements—increasing revenue by over 15% and increasing profit by over 10%.

Vaccine Equity and Occupational Health and Safety Analytics for COVID

From March 2020 through March 2022 a team from the U.S. Army Engineer Research and Development Center (ERDC) was constituted to develop a suite of innovative analytics applications to describe, predict, and inform COVID-19 risks and societal implications. Two key innovations developed for FEMA and ASPR Region I included (a) a vaccine equity modeling and analysis platform, and (b) a return-to-work simulator and decision support system. For (a), and in accordance with President Biden’s Executive Order 13995 (Ensuring an Equitable Pandemic Response and Recovery), ERDC’s Vaccine Equity Methodology included a three-step process to evaluate, at a county, state, regional, and national level, the various equity considerations and equity gaps relative to vaccine distribution and community uptake from March 2021 through January 2022. For (b), ERDC’s Workplace Micro-Exposure Model (MEM) was used to guide return-to-work decisions for emergency responders in Region 1 beginning Summer 2020. The MEM model harvested epidemiological forecast data and assessed workforce risk based on in-office participation against random-transit-events and building blueprints/population flow. Both tools were used to guide elements of the COVID emergency response effort, promoting a safer workforce as well as more responsive and equitable vaccine distribution efforts to various underserved communities across New England.

Analytical Pipeline for Identifying Potential Sex Trafficking Victims in Commercial Sex Ad Data

Sex trafficking refers to the use of force, fraud, or coercion for sexual exploitation and is facilitated by commercial sex ad websites. Each day, more than 100,000 new ads and more than 500,000 images are posted on these sites. Although ad data can provide important insights for counter-trafficking efforts, linking the large volume of ads is challenging. Additionally, scammers create ads seeking to obtain deposits via electronic payment methods. These ads do not correspond to legitimate individuals and add noise to the data-linking process. In 2020, the Institute of Data and Analytics (IDA) at The University of Alabama launched the Sex Trafficking Analytics for Network Detection and Disruption (STANDD) initiative. The STANDD team developed and maintains an analytical pipeline that utilizes novel technologies and methodologies from information systems, network science, and machine learning to remove anomalies due to scam ads, link the remaining data into groups representing individuals, and utilize these data groups for network and movement detection. Data products from this pipeline have helped law enforcement and non-profit organizations establish contact with more than 40 potential sex trafficking victims, many of whom are now connected with services to get them out of “the life.”

INFORMS Prize

This prize is awarded annually to the company that effectively integrates analytics into organizational decision-making, and has repeatedly applied ORMS principles in pioneering, novel and lasting ways. The 2023 winner will be recognized at the Edelman Gala on Monday evening and present their innovative O.R. work. on Tuesday afternoon.

Previous winners include BNSF Railway, Disney, U.S. Air Force, GM, Chevron, Memorial Sloan-Kettering Cancer Center, Sasol, Jeppesen, Intel, General Electric Global Research Center, Schneider National, Air Products and Chemicals, Procter & Gamble, UPS, Wayfair and other leading companies.

UPS George D. Smith Prize

The George D. Smith Prize is aimed at strengthening ties between academia and industry by rewarding institutions of higher education for effective and innovative preparation of students to be good practitioners of operations research. The Prize is generously underwritten by UPS. Awarded for the first time in 2012, past winners are Carnegie Mellon University, H. John Heinz III College, Sauder School of Business, University of British Columbia – Center for Operations Excellence, MIT Leaders for Global Operations, Naval Postgraduate School, and Tauber Institute for Global Operations at University of Michigan.

The teams will present their work to the judges on Sunday, April 16. The Smith Prize winner will be announced at the Edelman Gala on Monday, April 17 and the 2023 winner will give their presentation on Tuesday afternoon.