Abstract
Despite the importance of product returns, several less well understood issues still remain. In this paper, we propose a dynamic structural model that characterizes consumers’ sequential shopping trips for purchases and/or returns. We calibrate our proposed model to individual panel data in which we observe each consumer’s sequential shopping trips, including the number of products purchased and/or returned at each trip. Through our simulations, we find that product returns can also lead to desirable outcomes for retailers and that the ability to return purchased products incentivizes consumers to make more shopping trips and thus purchase more. Motivated by these observations, we also examine two possible return-based targeting policies: (1) targeted reduction of return cost and (2) targeted price promotion on return trips.
Similar content being viewed by others
Notes
The exception is Anderson et al. (2009), which will be discussed in the next paragraph.
While it is possible that consumers form the postpurchase perceived quality from a sequential set of signals from repeated usages, we are unable to directly incorporate such a specification into our model as we do not observe consumers’ usage behaviors. However, our flexible structure in the distribution of the perceived value signal can accommodate the possible averaging across multiple draws of signals. In particular, signal dig, r could be the average of a set of repeated random signal draws from usage experience (presumably from a different distribution with much greater variance) and ϑir the variance of the distribution related to the average of these random draws. This is another explanation for why we need to differentiate the distribution of perceived value signals from purchase and usage.
Alternatively, we can include RFM measures in the flow utility of purchases and returns when a trip is made.
To capture the effect of customer relationships, we can use the RFM measures to enter the utility associated with either the not purchase/return option or the return/purchase option.
We discretize the choice set of {Eit, Git} using the empirical distribution observed in the data by combining infrequently chosen purchases and return quantities in the same bucket.
Even in the absence of financial charges imposed by the firm, consumers might still incur opportunity costs from product returns (e.g., the cost to carry the returned products to the store). In our model, the marginal cost of return captures such opportunity costs.
We also checked the robustness of our counterfactual results under the model estimates with different levels of the normalized price coefficient. Results are not sensitive to these alternative specifications.
In all simulations described in this and the next sections, we update the state variables (number of products eligible for returns and RFM measures) on the basis of predicted consumer purchase and return decisions under each scenario.
The goal of simulations in this section is to quantify the impact of product returns rather than to propose alternative managerial strategies. Thus, whether the proposed scenario could be achieved in reality is less of concern. In the next two sections, we shift our focus to explore returns-based targeting strategies, in which we discuss in detail how retailers can implement each proposed strategy in reality.
We equate the number of trips being targeted with this price discount between the benchmark and the proposed policy.
When running the simulations, we also adjust consumers’ price expectations due to the additional price promotions. By doing so, the results reported from this policy simulation account for the potential strategic product return behaviors (e.g., consumers might purposefully make product returns to receive the targeted price discount).
The general idea of the IJC approach is to approximate the value functions by the average of their past realizations, as weighted by the difference between the state variables at the current iteration for the focal consumer and the state variables at past iterations for randomly selected consumers.
References
Abbey, J., Ketzenberg, M., & Metters, R. (2018). A more profitable approach to product returns. MIT Sloan Management Review, 60(1), 71–74.
Akçay, Y., Boyacı, T., & Zhang, D. (2013). Selling with money-back guarantees: The impact on prices, quantities, and retail profitability. Production and Operations Management, 22(4), 777–791. https://doi.org/10.1111/j.1937-5956.2012.01394.x.
Ali, F. (2019). A decade in review: Ecommerce sales vs. retail sales 2007-2018. Digital Commerce 360. Retrieved from https://www.digitalcommerce360.com/article/e-commerce-sales-retail-sales-ten-year-review/.
Altug, M. S., & Aydinliyim, T. (2016). Counteracting strategic purchase deferrals: The impact of online retailers’ return policy decisions. Manufacturing & Service Operations Management, 18(3), 376–392. https://doi.org/10.1287/msom.2015.0570.
Anderson, E. T., Hansen, K., & Simester, D. (2009). The option value of returns: Theory and empirical evidence. Marketing Science, 28(3), 405–423. https://doi.org/10.1287/mksc.1080.0430.
Appriss Retail (2018). Consumer returns in the retail industry. Retrieved from https://appriss.com/retail/wp-content/uploads/sites/4/2018/12/AR3018_2018-Customer-Returns-in-the-Retail-Industry_Digital.pdf/.
Bechwati, N. N., & Siegal, W. S. (2005). The impact of the prechoice process on product returns. Journal of Marketing Research, 42(3), 358–367.
Chen, Y., & Yao, S. (2016). Sequential search with refinement: Model and application with click-stream data. Management Science, 63(12), 4345–4365. https://doi.org/10.1287/mnsc.2016.2557.
Erdem, T., & Keane, M. P. (1996). Decision-making under uncertainty: Capturing dynamic brand choice processes in turbulent consumer goodsmarkets. Marketing science, 15(1), 1–20.
Erdem, T., Imai, S., & Keane, M. P. (2003). Brand and quantity choice dynamics under price uncertainty. Quantitative Marketing and Economics, 1(1), 5–64. https://doi.org/10.1023/A:1023536326497.
Ertekin, N. (2018). Immediate and long-term benefits of in-store return experience. Production and Operations Management, 27(1), 121–142. https://doi.org/10.1111/poms.12787.
Ertekin, N., Ketzenberg, M. E., & Heim, G. R. (2020). Assessing impacts of store and salesperson dimensions of retail service quality on consumer returns. Production and Operations Management, 29(4), 1232–1255.
Gallino, S., & Moreno, A. (2018). The value of fit information in online retail: Evidence from a randomized field experiment. Manufacturing & Service Operations Management, 20(4), 767–787. https://doi.org/10.1287/msom.2017.0686.
Hendel, I., & Nevo, A. (2006). Measuring the implications of sales and consumer inventory behavior. Econometrica, 74(6), 1637–1673.
Hsiao, L., & Chen, Y.-J. (2012). Returns policy and quality risk in e-business. Production and Operations Management, 21(3), 489–503. https://doi.org/10.1111/j.1937-5956.2011.01285.x.
Imai, S., Jain, N., & Ching, A. (2009). Bayesian estimation of dynamic discrete choice models. Econometrica, 77(6), 1865–1899. https://doi.org/10.3982/ECTA5658.
Ishihara, M., & Ching, A. T. (2019). Dynamic demand for new and used durable goods without physical depreciation: The case of Japanese video games. Marketing Science, 38(3), 392–416. https://doi.org/10.1287/mksc.2018.1142.
Krazy Coupon Lady. (2019a). Skip the Shipping Fees — Now You Can Take Amazon Returns to Kohl's!. Retrieved from https://thekrazycouponlady.com/tips/money/return-amazon-orders-kohls.
Krazy Coupon Lady. (2019b). 13 Target return policy secrets. Retrieved from https://thekrazycouponlady.com/tips/store-hacks/13-target-return-policy-secrets.
McWilliams, B. (2012). Money-back guarantees: Helping the low-quality retailer. Management Science, 58(8), 1521–1524. https://doi.org/10.1287/mnsc.1110.1497.
Moorthy, S., & Srinivasan, K. (1995). Signaling Quality with a Money-Back Guarantee: The Role of Transaction Costs. Marketing Science, 14(4), 442–466. https://doi.org/10.1287/mksc.14.4.442.
Narang, U., & Shankar, V. (2019). Mobile app introduction and online and offline purchases and product returns. Marketing Science, 38(5), 756–772. https://doi.org/10.1287/mksc.2019.1169.
Nevo, A., Turner, J. L., & Williams, J. W. (2016). Usage-based pricing and demand for residential broadband. Econometrica, 84(2), 411–443. https://doi.org/10.3982/ECTA11927.
O’Connor, C. (2015, April). How Maine bootmaker L.L. Bean became fashion's hottest company. Forbes. https://www.forbes.com/sites/clareoconnor/2015/03/25/how-maine-bootmaker-l-l-bean-became-fashions-hottest-company/#6623fc5a773d.
Ofek, E., Katona, Z., & Sarvary, M. (2011). “Bricks and clicks”: The impact of product returns on the strategies of multichannel retailers. Marketing Science, 30(1), 42–60. https://doi.org/10.1287/mksc.1100.0588.
Petersen, J. A., & Kumar, V. (2009). Are product returns a necessary evil? Antecedents and consequences. Journal of Marketing, 73(3), 35–51. https://doi.org/10.1509/jmkg.73.3.035.
Petersen, J. A., & Kumar, V. (2015). Perceived risk, product returns, and optimal resource allocation: Evidence from a field experiment. Journal of Marketing Research, 52(2), 268–285. https://doi.org/10.1509/jmr.14.0174.
Rekuc, D. (n.d.). Study: Why 92% of retail purchases still happen offline. Retrieved from https://ripen.com/blog/ecommerce_survey/.
Rust, J. (1987). Optimal replacement of GMC bus engines: An empirical model of Harold Zurcher. Econometrica, 55(5), 999–1033. https://doi.org/10.2307/1911259.
Sahoo, N., Dellarocas, C., & Srinivasan, S. (2018). The impact of online product reviews on product returns. Information Systems Research, 29(3), 723–738. https://doi.org/10.1287/isre.2017.0736.
Shulman, J. D., Coughlan, A. T., & Savaskan, R. C. (2009). Optimal restocking fees and information provision in an integrated demand-supply model of product returns. Manufacturing & Service Operations Management, 11(4), 577–594. https://doi.org/10.1287/msom.1090.0256.
Su, X. (2009). Optimal pricing with speculators and strategic consumers. Management Science, 56(1), 25–40. https://doi.org/10.1287/mnsc.1090.1075.
Turner, M. L. (2018). L.L. Bean announces end of “lifetime replacement policy,” institutes one-year limit on returns. Forbes. Retrieved from https://www.forbes.com/sites/marciaturner/2018/02/10/l-l-bean-announces-end-of-lifetime-replacement-policy-institutes-one-year-limit-on-returns/#33d83885f25f.
Acknowledgment
The article benefited from invaluable comments from the editor, the associate editor, and the three anonymous reviewers.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Shrihari Sridhar served as Area Editor for this article.
Supplementary Information
ESM 1
(DOCX 37 kb)
Appendix: Implementation
Appendix: Implementation
Computational details
Here, we specify our implementation of the IJC framework. We denote the parameter set as θi, which includes (1) shopping trip fixed cost (vi), (2) parameters related to purchase utility (i.e., mean (di) and variance of match value signals in-store (ϑi) and from usage experience (ϑi, r)), (3) decay parameters related to purchase utility (δi) and return cost (Ri), and (4) coefficients related to the RFM measures. Individual-specific parameters come from \( \left\{{\theta}_i\right\}\sim N\left(\overset{\sim }{\theta },{\sigma}_{\theta}^2\right) \).
Imai et al. (2009) propose a less computationally intensive approach to approximate value function using realizations of the past 100 iterations (N = 100). Suppose that we are at iteration r and have accumulated \( {H}^r={\left\{{\left\{{x}_i^k,\kern0.5em {\overset{\sim }{V}}^k\left({x}_i^k;{\theta}_i^k\right)\right\}}_{i=1}^I\right\}}_{k=r-N}^{r-1} \) through past iterations, where k denotes a given iteration before the current rth iteration, \( {x}_i^k \) and \( {\theta}_i^k \)are the set of state variables and parameters stored at each past iteration (to be discussed subsequently), and \( {\overset{\sim }{V}}^k\left({x}_i^k;{\theta}_i^k\right) \) is the value function associated with the stored state variables and parameters at each past iteration. Given that our model accommodates individual-specific parameters, in theory it requires us to store all state variables, parameters, and realized value functions for all consumers across all past iterations, which is computational costly. Thus, we adopt Imai et al.’s (2009) procedure to store one realization from one randomly selected consumer during each iteration. This simplification reduces the requirement for computer memory considerably. Within the rth iteration, the estimation procedure is extended as follows:
Step 1: Update * {θ i}
-
1.
We first draw a new set of parameter values of {θi} for each consumer using random walk. We denote the candidate draw as \( \left\{{\theta}_i^c\right\} \).
-
2.
To assess the value function, we must compute the EV(xi, t + 1). Following Imai et al. (2009), we can compute EV(xi, t + 1) using all past state variables, parameters, and realizations of value functions, as follows:
where INVi is the total number of products available for return and RFMi is the set of RFM measures. Given consumers’ current-period purchase and return decisions, we can compute INVi and RFMi deterministically; KhINV and KhRFM are their kernel density functions accordingly. The other two state variables—average price of purchased products, pi, and match value from usage experience dig, r—evolve stochastically.Footnote 12
-
3.
To compute the likelihood function, we must also integrate out the random match values. However, the complexity of our proposed model prevents us from analytically integrating out these two random match values. Following prior research (e.g., Erdem and Keane 1996), we draw 100 sets of random match values from their distributions (as specified in the main body of the paper) to integrate out the likelihood function.
-
4.
With the likelihood obtained with \( {\theta}_i^c \)and \( {\theta}_i^{r-1} \), we determine whether or not to accept the candidate parameter draw for a given individual.
Next, we repeat Step 1 to update individual-level parameters for every consumer.
Step 2: Update \( {\overset{\sim }{\boldsymbol{V}}}^{\boldsymbol{r}}\left({\boldsymbol{x}}_{\boldsymbol{i}}^{\boldsymbol{r}};{\boldsymbol{\theta}}^{\boldsymbol{r}}\right) \)
-
5.
The last step for iteration r involves computing the pseudo-value function \( {\overset{\sim }{V}}^r\left({x}_i^r;{\theta}_i^r\right) \), which can be done as follows:
-
i
Make one draw from the state space;
-
ii
Compute the expected future value;
-
iii
Apply the Bellman operator once.
-
i
-
6.
Proceed to the next iteration
State variables
Here, we now discuss the specification and law of motion associated with our state variables.
Number of products available for return
We specify the number of products available for return as INVit = INVi, t − 1 + Eit − Git. For simplicity of notation, we denote INVi, t − 1 as the number of products purchased before the current trips that are still within the window of return, Eit as the number of newly purchased items, and Git as the number of items returned during the current visit. As we do not observe consumers’ purchases from the very beginning, our proposed model is subject to a left-truncation issue (i.e., we do not observe INVi0). To address this issue, we first estimate a preliminary model, which has the same structure of our proposed model but with the assumption that INVi0 equals 0 (i.e., consumers have no items that are available to return at the beginning). With the model estimates, we then forward-simulate consumers’ purchases and returns 100 times randomly draw a set of initial INVi0 to estimate our proposed model.
RFM measures
Again, in our model, we include the following RFM measures: (1) the number of weeks from the most recent purchase (recency), (2) the number of shopping trips with purchases made in the recent quarter (frequency), and (3) the number of net spending in the recent quarter (monetary). Similar to inventory, all RFM measures are subject to left-truncation. We therefore use the same approach, as described previously, to handle the left-truncation issue with RFM measure.
Rights and permissions
About this article
Cite this article
Chen, J. A structural model of purchases, returns, and return-based targeting strategies. J. of the Acad. Mark. Sci. (2021). https://doi.org/10.1007/s11747-020-00761-z
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11747-020-00761-z