Abstract Meta-analysis is widely used to integrate results from multiple experiments to obtain generalized insights. Since meta-analysis datasets are often heteroscedastic due to varying subgroups and temporal heterogeneity arising from experiments conducted at different time points, the typical meta-analysis approach, which assumes homoscedasticity, fails to adequately address this heteroscedasticity among experiments. This paper proposes a new Bayesian estimation method that simultaneously shrinks estimates of the means and variances of experiments using a hierarchical Bayesian approach while accounting for time effects through a Gaussian process. This method connects experiments via the hierarchical framework, enabling “borrowing strength” between experiments to achieve high-precision estimates of each experiment’s mean. The method can flexibly capture potential time trends in datasets by modeling time effects with the Gaussian process. We demonstrate the effectiveness of the proposed method through simulation studies and illustrate its practical utility using a real marketing promotions dataset.
Jul 9, 2025
Abstract This study aims to investigate how different incentive sizes in multi-shot lottery promotions, including large and small prizes, influence subsequent consumer payments. Multi-shot lottery promotions allow repeated opportunities to win incentives and are widely used across various industries. Understanding the relationship between the cost of implementing the promotions, such as incentives for winning, and subsequent consumer payments, which drive revenue, is essential for improving cost-effectiveness. This study analyzes large-scale field data from over one million mobile payment service users and employs a stratified randomized experiment method that addresses user-initiated transaction bias. The results show that, during the promotion, winning any prize increases the total transaction amount (by $26.97–$32.80), the number of transactions (by 1.17–1.27), and the average transaction amount (by $8.81–$9.38). Notably, a small prize with a 0.2% return rate yields a return on investment of 1078.8%, surpassing the 5.6% and 8.6% from larger prizes. However, after the promotion, these differences in incentive size have negligible effects on consumer payments. Further analysis, which also examined whether the effects of winning vary depending on users’ frequency of use, reveals that these effects are most pronounced among light users across all outcomes. The findings suggest that allocating multiple small prizes may be more cost-effective than focusing on a few large prizes, especially for lower-usage segments, and offer valuable insights for designing successful multi-shot lottery promotions.
May 9, 2025
Abstract The number of investors holding risky assets in Japan is much lower than that in western countries even though it is an effective way for building investor assets. Although Japanese investment companies offer a service to invest in points through coalition loyalty programs instead of actual currency to address this situation, the problem still persists. One reason for this is that novice investors do not know in which stocks to invest. One possible solution is recommending stocks; however, we still face the cold-start problem because there is no transaction history for novice investors. In this study, we propose a novel content-based recommendation approach that utilizes touchpoint information, eg, payment and app usage data, on smartphones in daily life. This approach employs user-weighted recency, frequency, and monetary, called UW-RFM and a complementary module to comply with Japanese guidelines that prohibit presenting only a small number of companies and establishing a minimum number of companies to be presented. We conduct an online evaluation to validate the effectiveness of the proposed approach in an actual investment service. The evaluation results show that the proposed approach motivates users to invest more, ie, 0.352 more clicks on the recommendation area and 3,016 points (yen), than the baseline method that does not consider touchpoint information.
May 15, 2022