Mobile Money Fraud Prediction—A Cross-Case Analysis on the Efficiency of Support Vector Machines, Gradient Boosted Decision Trees, and Naïve Bayes Algorithms

Abstract

The onset of COVID-19 has re-emphasized the importance of FinTech especially in developing countries as the major powers of the world are already enjoying the advantages that come with the adoption of FinTech. Handling of physical cash has been established as a means of transmitting the novel corona virus. Again, research has established that, been unbanked raises the potential of sinking one into abject poverty. Over the years, developing countries have been piloting the various forms of FinTech, but the very one that has come to stay is the Mobile Money Transactions (MMT). As mobile money transactions attempt to gain a foothold, it faces several problems, the most important of them is mobile money fraud. This paper seeks to provide a solution to this problem by looking at machine learning algorithms based on support vector machines (kernel-based), gradient boosted decision tree (tree-based) and Naïve Bayes (probabilistic based) algorithms, taking into consideration the imbalanced nature of the dataset. Our experiments showed that the use of gradient boosted decision tree holds a great potential in combating the problem of mobile money fraud as it was able to produce near perfect results.

The determinants of investment fraud: A machine learning and artificial intelligence approach

“…A member of the ensemble family gradient boosting is a technique where each decision tree is a sequence that tries to correct the prediction errors of the previous tree so that the present tree is always better than the one before (Botchey et al, 2020 , p. 8). Gradient boosting trains a set of weak learners and converts them into a single strong learner (Botchey et al, 2020 ). These predictions are then utilized for training the second weak learner, and so forth.…”

“…First, it is important to carefully tune the hyperparameters, particularly the learning rate (Hammou et al, 2021 ). Second, gradient boosting is relatively insensitive to overfitting, meaning that it can be used to train large models with high accuracy (Botchey et al, 2020 ). Third, gradient boosting is computationally efficient, making it a good choice for large-scale machine learning tasks (Botchey et al, 2020 ).…”

“…Machine learning is a promising approach for detecting fraud, as it can learn to identify patterns of behavior indicative of fraud (Lokanan and Sharma, 2022 ). Supervised machine learning algorithms can be trained on labeled data to classify transactions as either fraudulent or non-fraudulent (Fayzrakhmanov et al, 2018 ; Botchey et al, 2020 ). Once trained, these algorithms can be deployed in production to flag suspected fraudulent transactions automatically.…”

“…Similarly, insurance fraud can be detected by looking for patterns in claims data that are not representative of the general population (Wang and Xu, 2018 ). The challenge with fraud detection is that it is often difficult to obtain enough training data to train a machine learning model (see Botchey et al, 2020 ; Lokanan and Sharma, 2022 ). Also, the distribution of fraudulent data may be very different from the distribution of non-fraudulent data.…”

Applications of Machine Learning (ML) - The real situation of the Vietnam Fintech Market

“…Hence, the fundamental goal of asset pricing is to know the behaviour of risk premiums; however, risk premiums are very difficult to measure. Botchey et al (2020) give three main reasons why investors prefer machine learning methods in asset pricing.…”