Safer Together: Machine Learning Models Trained on Shared Accident Datasets Predict Construction Injuries Better than Company-Specific Models
This addresses the challenge of limited data for small companies in the construction industry by enabling cross-organizational learning, though it is incremental as it builds on existing machine learning methods.
The study tackled the problem of predicting construction injuries by comparing models trained on shared accident datasets from multiple companies against company-specific models, finding that generic models outperformed specific ones in most cases and provided more detailed forecasts.
In this study, we capitalized on a collective dataset repository of 57k accidents from 9 companies belonging to 3 domains and tested whether models trained on multiple datasets (generic models) predicted safety outcomes better than the company-specific models. We experimented with full generic models (trained on all data), per-domain generic models (construction, electric T&D, oil & gas), and with ensembles of generic and specific models. Results are very positive, with generic models outperforming the company-specific models in most cases while also generating finer-grained, hence more useful, forecasts. Successful generic models remove the needs for training company-specific models, saving a lot of time and resources, and give small companies, whose accident datasets are too limited to train their own models, access to safety outcome predictions. It may still however be advantageous to train specific models to get an extra boost in performance through ensembling with the generic models. Overall, by learning lessons from a pool of datasets whose accumulated experience far exceeds that of any single company, and making these lessons easily accessible in the form of simple forecasts, generic models tackle the holy grail of safety cross-organizational learning and dissemination in the construction industry.