Challenges and opportunities in applying Neural Temporal Point Processes to large scale industry data
This work addresses scalability and robustness issues for NTPP models in industry applications like customer behavior analysis, but it is incremental as it builds on existing methods with new data and minor modifications.
The study investigated applying Neural Temporal Point Processes (NTPP) to large-scale industry data, identifying challenges such as vulnerability to dataset imbalances and scalability issues, and proposed a novel parametrization using static user features to address cold-start problems.
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.