PAI 1

Important results from the project

The aim of the project was to apply AI in the risk mitigation process to increase the proactiveness in project start-up phase. Also, Plan B aimed to increase their knowledge in machine learning to drive the company’s development in the construction sector. A Machine Learning pipeline that helps automate classification algorithms has been constructed and Plan B has gained great insights into Machine Learning and the feasibility and quality of their existing datasets.

Expected long term effects

A Machine Learning pipeline that helps automate classification algorithms has been constructed. Insights in crucial factors that affect the quality of the data in the Machine Learning model have been gained and will be implemented in upcoming projects in order to take the next step in Plan B’s Machine Learning journey.

Approach and implementation

The constructed pipeline pre-processes and transforms the original dataset into a model that can be analyzed, tested and, finally evaluated. Unfortunately, the models show a rather poor result. However, we believe that the constructed models are per sé not the reason for the bad performance, instead, we think it is because of the quality of the dataset used. As soon as a new dataset is prepared, we will run the pipeline and evaluate the outcome.