Search for: All records

Online marketplaces use rating systems to promote the discovery of high-quality products. However, these systems also lead to high variance in producers' economic outcomes: a new producer who sells high-quality items, may unluckily receive a low rating early, severely impacting their future popularity. We investigate the design of rating systems that balance the goals of identifying high-quality products (``efficiency'') and minimizing the variance in outcomes of producers of similar quality (individual ``producer fairness'').We show that there is a trade-off between these two goals: rating systems that promote efficiency are necessarily less individually fair to producers. We introduce prior-weighted rating systems as an approach to managing this trade-off. Informally, the system we propose sets a system-wide prior for the quality of an incoming product; subsequently, the system updates that prior to a posterior for each product's quality based on user-generated ratings over time. We show theoretically that in markets where products accrue reviews at an equal rate, the strength of the rating system's prior determines the operating point on the identified trade-off: the stronger the prior, the more the marketplace discounts early ratings data (increasing individual fairness), but the slower the platform is in learning about true item quality (so efficiency suffers). We further analyze this trade-off in a responsive market where customers make decisions based on historical ratings. Through calibrated simulations in 19 different real-world datasets sourced from large online platforms, we show that the choice of prior strength mediates the same efficiency-consistency trade-off in this setting. Overall, we demonstrate that by tuning the prior as a design choice in a prior-weighted rating system, platforms can be intentional about the balance between efficiency and producer fairness. 

Abstract ContextYouth with type 1 diabetes (T1D) struggle to meet and sustain hemoglobin A1c (HbA1c) targets. Youth enrolled in the Pilot 4T Study improved HbA1c by 0.5% at 1 year, compared to historical controls. ObjectiveTo assess 3 years of glycemic outcomes in the Pilot 4T Study. MethodsThe Pilot 4T Extension cohort was prospectively followed to determine changes in HbA1c and continuous glucose monitoring (CGM) metrics over 3 years at the Stanford Medicine Children's Health Diabetes Clinic. Youth with T1D in the Pilot 4T Study enrolled in the extension phase started CGM in the first month of diabetes diagnosis, received intensified education and remote patient monitoring (RPM) weekly for the first year of diabetes diagnosis, and monthly RPM in the extension phase. HbA1c and CGM metrics were evaluated over the first 3 years of diagnosis. ResultsIn the Pilot 4T cohort, 78.5% (n = 102) of participants enrolled in the study extension phase and were followed through 3 years. The adjusted difference in HbA1c at 3 years was 1.2% (95% CI 0.7%-1.7%) lower in the Pilot 4T cohort than in the Historical cohort. In the Pilot 4T cohort, 68% and 37% met the <7.5% and <7% HbA1c targets at 3 years, respectively, compared to 37% and 20% in the Historical cohort. ConclusionYouth with T1D in the Pilot 4T extension phase sustained improvements in HbA1c over 3 years. Focusing resources on intensive management during the first year after T1D diagnosis may impact long-term glycemia. 

Background:Youth with type 1 diabetes (T1D) and public insurance have lower diabetes technology use. This pilot study assessed the feasibility of a program to support continuous glucose monitor (CGM) use with remote patient monitoring (RPM) to improve glycemia for youth with established T1D and public insurance. Methods:From August 2020 to June 2023, we provided CGM with RPM support via patient portal messaging for youth with established T1D on public insurance with challenges obtaining consistent CGM supplies. We prospectively collected hemoglobin A_1c(HbA_1c), standard CGM metrics, and diabetes technology use over 12 months. Results:The cohort included 91 youths with median age at enrollment 14.7 years, duration of diabetes 4.4 years, 33% non-English speakers, and 44% Hispanic. Continuous glucose monitor data were consistently available (≥70%) in 23% of the participants. For the 64% of participants with paired HbA_1cvalues at enrollment and study end, the median HbA_1cdecreased from 9.8% to 9.0% ( P < .001). Insulin pump users increased from 31 to 48 and automated insulin delivery users increased from 11 to 38. Conclusions:We established a program to support CGM use in youth with T1D and barriers to consistent CGM supplies, offering lessons for other clinics to address disparities with team-based, algorithm-enabled, remote T1D care. This real-world pilot and feasibility study noted challenges with low levels of protocol adherence and obtaining complete data in this cohort. Future iterations of the program should explore RPM communication methods that better align with this population’s preferences to increase participant engagement. 

Hybrid models composing mechanistic ODE- based dynamics with flexible and expressive neural network components have grown rapidly in popularity, especially in scientific domains where such ODE-based modeling offers important interpretability and validated causal grounding (e.g., for counterfactual reasoning). The incorporation of mechanistic models also provides inductive bias in standard blackbox modeling approaches, critical when learning from small datasets or partially observed, complex systems. Unfortunately, as the hybrid models become more flexible, the causal grounding provided by the mechanistic model can quickly be lost. We address this problem by leveraging another common source of domain knowledge: ranking of treatment effects for a set of interventions, even if the precise treatment effect is unknown. We encode this information in a causal loss that we combine with the standard predictive loss to arrive at a hybrid loss that biases our learning towards causally valid hybrid models. We demonstrate our ability to achieve a win-win, state-of-the-art predictive performance and causal validity, in the challenging task of modeling glucose dynamics post-exercise in individuals with type 1 diabetes. 

We develop an analytical framework to study experimental design in two-sided marketplaces. Many of these experiments exhibit interference, where an intervention applied to one market participant influences the behavior of another participant. This interference leads to biased estimates of the treatment effect of the intervention. We develop a stochastic market model and associated mean field limit to capture dynamics in such experiments and use our model to investigate how the performance of different designs and estimators is affected by marketplace interference effects. Platforms typically use two common experimental designs: demand-side “customer” randomization ([Formula: see text]) and supply-side “listing” randomization ([Formula: see text]), along with their associated estimators. We show that good experimental design depends on market balance; in highly demand-constrained markets, [Formula: see text] is unbiased, whereas [Formula: see text] is biased; conversely, in highly supply-constrained markets, [Formula: see text] is unbiased, whereas [Formula: see text] is biased. We also introduce and study a novel experimental design based on two-sided randomization ([Formula: see text]) where both customers and listings are randomized to treatment and control. We show that appropriate choices of [Formula: see text] designs can be unbiased in both extremes of market balance while yielding relatively low bias in intermediate regimes of market balance. This paper was accepted by David Simchi-Levi, revenue management and market analytics.