Keyword

Impact measurement, Synthetic control, Assortment Optimization, Retail Industry, heterogeneous treatment effects, hypothesis testing

Abstract

This study offers an innovative method for evaluating the effects of assortment changes on retail store revenue, employing the Synthetic Control Method (SCM) with Lasso regression. In response to the limitations of randomized control trials for large-scale interventions, we propose a unique approach using Lasso regression to build synthetic control groups from comparable stores in competitor retailers. This innovative technique overcomes the obstacle of absent control data within the same retailer. Our analysis reveals a remarkable 3.7% increase in retailer revenue after implementing the assortment changes. To confirm the validity of our findings, we conducted placebo studies, solidifying the positive impact of these adjustments. These results advocate embracing the SCM with Lasso regression as a reliable tool for measuring the effects of interventions in the business world, especially when controlled experiments are not feasible. This method empowers retailers to assess the effectiveness of assortment optimization strategies and make data-driven decisions about future changes.


Full Text : PDF
References
  • Abadie A, Gardeazabal J. (2003). The economic costs of conflict: A case study of the Basque Country. American Economic Review 93: 113–132
  • Abadie A. 2005. Semiparametric difference‐in‐differences estimators. The Review of Economic Studies 72: 1–19
  • Athey, S. and Imbens, G.W. (2006), “Identification and Inference in Nonlinear Difference-inDifferences Models”, Econometrica , vol. 74, no. 2, 431-497.
  • Begay, M., Traynor, M., and Glantz, S. (1993), “The Tobacco Industry, State Politics, and Tobacco Education in California”, American Journal of Public Health, vol. 83, no. 9, 1214-1221
  • Bertrand, M., Duflo, E., and Mullainathan, S. (2004), “How Much Should We Trust Differences-in-Differences Estimates?”, Quarterly Journal of Economics, vol. 119, no. 1, 249-275.
  • Abadie, A. and G. W. Imbens (2011). Bias-corrected matching estimators for average treatment effects. Journal of Business & Economic Statistics 29 (1), 1–11
  • Abadie, A. and J. L’Hour (2018). A penalized synthetic control estimator for disaggregated data
  • Ando, M. and F. S¨avje (2013). Hypothesis testing with the synthetic control method
  • Botosaru, I. and B. Ferman (2017). On the role of covariates in the synthetic control method
  • Mitze  T, Kosfeld  R, Rode  J, et al.(2020)  Face masks considerably reduce COVID-19 cases in Germany. Proc Natl Acad Sci U S A. 2020;117(51):32293–3230
  • Dimick  JB, Ryan  AM(2014). Methods for evaluating changes in health care policy: the difference-in-differences approach. JAMA. 2014;312(22):2401–2402.
  • Doudchenko  N, Imbens  GW.(2017)  Balancing, regression, difference-in-differences and synthetic control methods: a synthesis [preprint]. arXiv. 2017. ttp://arxiv.org/abs/1610.07748
  • Bertrand  M, Duflo  E, Mullainathan(2004)  S. How much should we trust differences-in-differences estimates?  Q J Econ. 2004;119(1):249–275
  • Ferman  B, Pinto  C. (2019) Inference in differences-in-differences with few treated groups and heteroskedasticity. Rev Econ Stat. 2019;101(3):452–467
  • Becker  M, Klößner  S(2018). Fast and reliable computation of generalized synthetic controls. Econ Stat. 2018;5:1–19.
  • Cassel, C. M., C.-E. Sarndal, and J. H. Wretman (1976). Some results on generalized difference estimation and generalized regression estimation for finite population. Biometrika 63 (3), 615–620.