A Concert-planning Tool for Independent Musicians by Machine Learning Models

TL;DR

This paper develops a machine learning-based tool to assist independent musicians in selecting concert locations by analyzing industry agglomeration effects, with a focus on classification models for location prediction.

Contribution

The study shifts from pricing advice to location classification, demonstrating that Random Forest models significantly improve concert location recommendations for musicians.

Findings

Concert price varies little across different factors.

Random Forest achieves 316% better classification performance.

Location choice can be effectively predicted using machine learning models.

Abstract

Our project aims at helping independent musicians to plan their concerts based on the economies of agglomeration in the music industry. Initially, we planned to design an advisory tool for both concert pricing and location selection. Nonetheless, after implementing SGD linear regression and support vector regression models, we realized that concert price does not vary significantly according to different music types, concert time, concert location and ticket venues. Therefore, to offer more useful suggestions, we focus on the location choice problem by turning it to a classification task. The overall performance of our classification model is pretty good. After tuning hyperparameters, we discovered the Random Forest gives the best performance, improving the classification result by 316%. This result reveals that we could help independent musicians better locate their concerts to where similar musicians would go, namely a place with higher network effects.