# Practical Processing of Mobile Sensor Data for Continual Deep Learning Predictions

## TL;DR

This paper introduces a practical method for processing mobile sensor data to enable continual deep learning predictions, demonstrating improved notification attendance prediction with reduced feature engineering.

## Contribution

The paper presents a comprehensive pipeline for mobile sensor data processing that enhances continual prediction accuracy without extensive feature engineering.

## Key findings

- 40% performance increase over baseline
- Achieved AUC of 0.702 in prediction task
- Effective in real-world mobile sensor data scenarios

## Abstract

We present a practical approach for processing mobile sensor time series data for continual deep learning predictions. The approach comprises data cleaning, normalization, capping, time-based compression, and finally classification with a recurrent neural network. We demonstrate the effectiveness of the approach in a case study with 279 participants. On the basis of sparse sensor events, the network continually predicts whether the participants would attend to a notification within 10 minutes. Compared to a random baseline, the classifier achieves a 40% performance increase (AUC of 0.702) on a withheld test set. This approach allows to forgo resource-intensive, domain-specific, error-prone feature engineering, which may drastically increase the applicability of machine learning to mobile phone sensor data.