# A Nonparametric Bayes Approach to Online Activity Prediction

arXiv: https://arxiv.org/abs/2401.14722 · HTML: https://mlsanity.com/paper/2401.14722/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 27 references that are in the map.
- First posted on arXiv 26 Jan 2024.

## Builds on (most cited first, 7 of 7)

- [Designing and Deploying Online Field Experiments](https://mlsanity.com/paper/1409.3174/) (2014)
- [A Bayesian Model for Online Activity Sample Sizes](https://mlsanity.com/paper/2111.12157/) (2021)
- [Posteriors, conjugacy, and exponential families for completely random measures](https://mlsanity.com/paper/1410.6843/) (2014)
- [More for less: Predicting and maximizing genetic variant discovery via Bayesian nonparametrics](https://mlsanity.com/paper/1912.05516/) (2019)
- [Transform-scaled process priors for trait allocations in Bayesian nonparametrics](https://mlsanity.com/paper/2303.17844/) (2023)
- [Scaled process priors for Bayesian nonparametric estimation of the unseen genetic variation](https://mlsanity.com/paper/2106.15480/) (2021)
- [The combinatorial structure of beta negative binomial processes](https://mlsanity.com/paper/1401.0062/) (2013)

## Abstract (arXiv)

Accurately predicting the onset of specific activities within defined timeframes holds significant importance in several applied contexts. In particular, accurate prediction of the number of future users that will be exposed to an intervention is an important piece of information for experimenters running online experiments (A/B tests). In this work, we propose a novel approach to predict the number of users that will be active in a given time period, as well as the temporal trajectory needed to attain a desired user participation threshold. We model user activity using a Bayesian nonparametric approach which allows us to capture the underlying heterogeneity in user engagement. We derive closed-form expressions for the number of new users expected in a given period, and a simple Monte Carlo algorithm targeting the posterior distribution of the number of days needed to attain a desired number of users; the latter is important for experimental planning. We illustrate the performance of our approach via several experiments on synthetic and real world data, in which we show that our novel method outperforms existing competitors.