Using a Machine Learning Approach to Implement and Evaluate Product Line Features

TL;DR

This paper explores using machine learning to model and evaluate predictive features for bike-sharing systems, enabling better assessment of feature performance and system behavior before deployment.

Contribution

It introduces a machine learning framework for modeling and evaluating system features based on usage logs, aiding in cost-performance trade-off analysis.

Findings

Machine learning models effectively predict system states.

Predictive performance metrics assist in feature evaluation.

Framework supports pre-deployment assessment of features.

Abstract

Bike-sharing systems are a means of smart transportation in urban environments with the benefit of a positive impact on urban mobility. In this paper we are interested in studying and modeling the behavior of features that permit the end user to access, with her/his web browser, the status of the Bike-Sharing system. In particular, we address features able to make a prediction on the system state. We propose to use a machine learning approach to analyze usage patterns and learn computational models of such features from logs of system usage. On the one hand, machine learning methodologies provide a powerful and general means to implement a wide choice of predictive features. On the other hand, trained machine learning models are provided with a measure of predictive performance that can be used as a metric to assess the cost-performance trade-off of the feature. This provides a principled way to assess the runtime behavior of different components before putting them into operation.