PROMOTION ABUSE FRAUD APPLICATION DEVELOPMENT USING RISK SCORING METHOD

• Main Author: Naya Aprisadianti, Shafira
• Format: Final Project
• Language: Indonesia
• Online Access: https://digilib.itb.ac.id/gdl/view/76665
• Institution: Institut Teknologi Bandung

Promotion abuse fraud is promotion abuse by duplicating accounts to gain advantage over promotional codes fraudulently. This action is very detrimental to the company. Therefore, this study aims to deal with fraud by developing an application to detect promotion abuse fraud. The application development process includes needs analysis, modeling, and application development. The dataset used for modeling comes from an e- commerce company in Indonesia. The dataset collection stage includes calculating the similarity between accounts using the Levenshtein distance similarity algorithm to get additional features, such as the number of accounts that are similar to an account. At the modeling stage, experiments were carried out using the Random Forest algorithm and a risk scoring algorithm based on machine learning, namely FasterRisk. The FasterRisk algorithm results model is superior for fraud detection cases with a higher F1 score and AUC than the Random Forest with an F1 score of 0.316 and an AUC score of 0.666. The FasterRisk model also has an advantage in terms of interpretability because it has an output in the form of a more understandable risk score model, so users can understand the factors that are indicators of fraud. The FasterRisk algorithm result model is then deployed into a web application. The application built has several features, such as displaying the results of fraud detection using the FasterRisk algorithm, simulating several risk score models, displaying additional information about the model, downloading predicted data, and being able to block accounts that are predicted to be fraudulent.