Abstract: In some implementations, a planning system may receive multiple files in multiple formats and associated with historical contracting information. The planning system may convert the plurality of files into a unified data format, to generate a unified set of data, and may update a machine learning model based on the unified set of data. The planning system may receive input associated with a current contract and may select a set of factors based on a phase associated with the current contract. The planning system may apply the machine learning model to the input to generate a probability associated with the current contract and may provide instructions for a user interface that visually depicts the probability. The planning system may additionally generate recommended modifications to increase the probability. The recommended modifications may be fed back into a training (and retraining) cycle for the machine learning model to increase accuracy.