Which will be your firm's next technology? Comparison between machine learning and network-based algorithms

TL;DR

This paper compares machine learning and network-based algorithms to forecast firms' future technological sectors based on patenting activity, finding that tree-based machine learning methods outperform traditional network approaches.

Contribution

The study introduces a novel comparison showing that tree-based machine learning algorithms better predict firms' future innovation sectors than standard network-based methods.

Findings

Tree-based machine learning algorithms outperform network-based methods.

The methodology helps identify feasible versus out-of-reach technological sectors.

The approach can be used by firms and policymakers for strategic innovation planning.

Abstract

We reconstruct the innovation dynamics of about two hundred thousand companies by following their patenting activity for about ten years. We define the technological portfolios of these companies as the set of the technological sectors present in the patents they submit. By assuming that companies move more frequently towards related sectors, we leverage on their past activity to build network-based and machine learning algorithms to forecast the future submission of patents in new sectors. We compare different evaluation metrics and prediction methodologies, showing that tree-based machine learning algorithms overperform the standard methods based on networks of co-occurrences. This methodology can be applied by firms and policymakers to disentangle, given the present innovation activity, the feasible technological sectors from those that are out of reach, given their present innovation activity.