Weighted Multi-Level Feature Factorization for App ads CTR and installation prediction

TL;DR

This paper introduces Weighted Multi-Level Feature Factorization, a neural network approach for predicting app ad click-through and installation probabilities, emphasizing feature interactions and task-specific modeling to improve deep funnel optimization while respecting user privacy.

Contribution

The paper presents a novel neural network model that separately models click and install probabilities using shared and task-specific features, enhancing prediction accuracy in app ad campaigns.

Findings

Achieved 11th place in ACM RecSys Challenge 2023

Demonstrated effectiveness of multi-level feature interaction modeling

Released source code for reproducibility

Abstract

This paper provides an overview of the approach we used as team ISISTANITOS for the ACM RecSys Challenge 2023. The competition was organized by ShareChat, and involved predicting the probability of a user clicking an app ad and/or installing an app, to improve deep funnel optimization and a special focus on user privacy. Our proposed method inferring the probabilities of clicking and installing as two different, but related tasks. Hence, the model engineers a specific set of features for each task and a set of shared features. Our model is called Weighted Multi-Level Feature Factorization because it considers the interaction of different order features, where the order is associated to the depth in a neural network. The prediction for a given task is generated by combining the task specific and shared features on the different levels. Our submission achieved the 11 rank and overall score of 55 in the competition academia-track final results. We release our source code at: https://github.com/knife982000/RecSys2023Challenge