Faced with growing competition in the microfinancing market and higher operational risk, it is ever more important for a Microfinancing Institution (MFI) to be able to leverage less conventional customer data to improve the efficiency of their lending models. Most MFIs are active in Malaysia where financial history is generally non-existent on their user base which increases the difficulty in assessing the credit worthiness of individuals. Instead, an alternative source of data such as mobile phone call and SMS logs can be utilised to assist with this problem. In this project, call and SMS logs from the loan applicants are featured and used to train various classification models. PITEH is an Android mobile lending application that offers microfinance ranging from RM500 - RM5,000 by validating the creditworthiness of a loan applicant through the creation of credit scores using machine learning to classify data existing in the call and SMS logs. With users' explicit permission, the application will collect key pieces of data from users' Android devices solely for the purposes of underwriting loan applicants who do not have documented financial history. It will select these data sources for the purposes of understanding a user's potential financial capacity, his or her behavioural attributes, and to validate his identity. With something as simple as a credit score, we are giving people the power to build their own futures. © 2020 IEEE.