No abstract

Online commerce gives companies not only a growing global sales platform, but also powerful consumers enjoying 24/7 availability, choice proliferation and the power to opt in and out permission-based communication. Unfortunately, our knowledge is limited on long-term marketing effectiveness in this space and on how it differs across customer segments. Managers appear overwhelmed by the combination of rich online data on hundreds of thousands of customers and the typical aggregate-level data on offline marketing spending. This paper is the first to investigate the long-term impact of coupon promotions, TV, radio, print, and Internet advertising across customer segments for a major digital music provider with over 500,000 customers. We first segment customers and subsequently analyze how these segments respond in the long run to different marketing activities when purchasing music downloads. Our findings reveal that the effectiveness of marketing differs across segments, while standard segmentation approaches fail to identify the most valuable catches in a sea of consumers. In contrast to empirical generalizations on consumer packaged goods, heavy users of digital music products are least sensitive to price and most sensitive to TV advertising and to multiple touch points. Light users, the majority of consumers, are price sensitive and tend to opt out of targeted communication. Our research enables managers in the digital media space to target high-value customer segments with the most effective actions.

SARS-CoV-2 has caused a deadly pandemic worldwide, placing a burden on local health care systems and economies. Infection rates with SARS-CoV-2 and the related mortality of COVID-19 are not equal among countries or even neighboring regions. Based on data from official German health authorities since the beginning of the pandemic, we developed a case-fatality prediction model that correctly predicts COVID-19-related death rates based on local geographical developments of infection rates in Germany, Bavaria, and a local community district city within Upper Bavaria. Our data point towards the proposal that local individual infection thresholds, when reached, could lead to increasing mortality. Restrictive measures to minimize the spread of the virus could be applied locally based on the risk of reaching the individual threshold. Being able to predict the necessity for increasing hospitalization of COVID-19 patients could help local health care authorities to prepare for increasing patient numbers.