Challenges and opportunities in applying Neural Temporal Point Processes to large scale industry data

Abstract

In this work, we identify open research opportunities in applying Neural Temporal Point Process (NTPP) models to industry scale customer behavior data by carefully reproducing NTPP models published up to date on known literature benchmarks as well as applying NTPP models to a novel, real world consumer behavior dataset that is twice as large as the largest publicly available NTPP benchmark. We identify the following challenges. First, NTPP models, albeit their generative nature, remain vulnerable to dataset imbalances and cannot forecast rare events. Second, NTPP models based on stochastic differential equations, despite their theoretical appeal and leading performance on literature benchmarks, do not scale easily to large industry-scale data. The former is in light of previously made observations on deep generative models. Additionally, to combat a cold-start problem, we explore a novel addition to NTPP models -a parametrization based on static user features.

Gen Z’s Motivations towards Sustainable Fashion and Eco-Friendly Brand Attributes: The Case of Vinted

“…Vinted is a unicorn, "a privately owned start-up company, which has reached a valuation of $1 billion or more" [17] (p. 5). Additionally, it is a clear example of industry 4.0 since digitalization is in the DNA of its business model and execution [18,19], encompassing full-comprehensive intelligent networking of technology and process.…”

“…This point of view constitutes the novelty and originality of the research since most of the studies address the case of Vinted by analyzing its business model, the role played in industry 4.0, and its impact on sustainability [15][16][17][18][19][20][21], without analyzing the motivations of Gen Z toward sustainable fashion and eco-friendly brand attributes.…”