Credit-worthiness Prediction in Energy-Saving Finance using Machine Learning Model

Abstract

Companies can form their own "ESCO model" with their capitals. New opportunities that Energy Saving Company (ESCO) can do was to offer PSS business model in the form of Energy Saving Agreement (ESA) or Energy Saving Performance Contract (ESPC), which was known as "saving back arrangement financing." ESCO contracts could free business owners from new upfront investment. Unfortunately, customer's creditworthiness was becoming more crucial for ESCO. Machine learning was used to predict the creditworthiness of clients in ESCO financing processes. This research aimed to develop a scoring model to leverage a machine learning and life cycle cost analysis (LCCA) to evaluate alternative financing for Energy Saving in Indonesia. Research from the case studies leads to a clearer understanding of the factors that affect all parties' decisions to implement and continue with their ESCO project. Both considerations, technology, and administration emerge from this case study which greatly influenced the participants to adopt the decision and continue with the ESCO project. In contrast, both parties agreed to solve the credit risk constraints on the project. This study indicates that administration influences were more significant than the technological factor in shaping their decisions.