Predicting Fraud in Mobile Money Transactions using Machine Learning: The Effects of Sampling Techniques on the Imbalanced Dataset

Botchey, Francis Effirim; Qin, Zhen; Hughes-Lartey, Kwesi; Ampomah, Ernest Kwame

doi:10.31449/inf.v45i7.3179

Cited by 5 publications

(3 citation statements)

References 39 publications

(52 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is evaluated how well the ensemble approaches perform [49]. The effectiveness of the various sampling approaches is examined [50]. Machine learning methods were compared in this investigation [51].…”

Section: Learning Imbalanced Streams From Nonstationary Environmentsmentioning

confidence: 99%

Analyzing Adaptive and Non-Adaptive Online Learners on Imbalanced Evolving Streams

Himaja¹,

Dondeti²,

Srilakshmi³

2023

IJCAI

View full text Add to dashboard Cite

The online class imbalance and concept drift (OCI-CD) has recently received much interest. The impact of this combined problem on state-of-the-art of online adaptive and non-adaptive learners has received little attention. This study investigates the effect of parameters such as current imbalance ratio, stream length, drift type, drift levels, and imbalance state (static or dynamic) on adaptive and non-adaptive online learners. The experimental results show that each parameter considered for the study has a significant impact on learner performance: (a) minority class performance decreases as the degree of imbalance increases, (b) non-adaptive learners are much susceptible to class imbalance, concept drift, and the combined problem of both drifts than adaptive learners, (c) adaptive learners are only susceptible to class imbalance drifts, and (d) the impact of the dynamic degree of imbalance is more on learner than static (e) the adaptive large scale support vector machine yields stable performance to all the parameters considered for the study. Based on these findings, directions for developing new approaches are also presented. Povzetek: Analizirane so razne metode strojnega učenja glede na parametre učenja, recimo spreminjanje neuravnoteženja razredov.

show abstract

Section: Learning Imbalanced Streams From Nonstationary Environmentsmentioning

confidence: 99%

Analyzing Adaptive and Non-Adaptive Online Learners on Imbalanced Evolving Streams

Himaja¹,

Dondeti²,

Srilakshmi³

2023

IJCAI

View full text Add to dashboard Cite

show abstract

“…Various pre-processing procedures or data transformation methods have been employed to enhance the data quality and, subsequently, the classification accuracy of the Financial Inclusion dataset [18]. ML algorithms are increasingly being used to predict fraudulent transactions.…”

Section: Introductionmentioning

confidence: 99%

Performance Evaluation of Machine Learning Models for Cyber Threat Detection and Prevention in Mobile Money Services

Akinyemi

Olalere²,

Sanni

et al. 2023

IJCAI

View full text Add to dashboard Cite

In this paper, an investigation was made to evaluate the effectiveness of the different classifiers suitable to predict the probability of a cyber-threat or fraudulent intent applicant during the Mobile Money Service on-boarding or service activation process, with the goal of determining the best machine learning model for the predictive model solution. Experimental work was carried out by formulating cyber threat predictive models using six supervised machine learning algorithms: Logistic regression(LR), Naïve Bayes, Shallow Neural Network (SNN), Deep Neural Network (DNN), Classification and Regression Trees (CART) and Random Forest (RF) of different configurations. Each model was simulated with both Synthetic Minority Operation Techniques (SMOTE) and without SMOTE (No-SMOTE) on 25,000 records of mobile money applicants. Twenty-four ( 24) different configurations of the formulated predictive models were simulated and evaluated using the Python programming language. Simulation results of the predictive models proved that the Random Forest model multiclass configurations with the SMOTE dataset outperformed all other configurations. The results also showed that the multiclass experiments with SMOTE had better performance than the binary configurations with NO-SMOTE in the predictive models. The study concluded that using the Random Forest-based predictive machine learning model will increase the security level of the Mobile Money solution by detecting and preventing anomalous customer registrations during the unbanked onboarding process.Povzetek: Napovedovanje kibernetskih groženj mobilnega denarja z uporabo algoritmov strojnega učenja. 22 RF Binary-SMOTE Random Forest(RF) with Binary feature configuration and with SMOTE application to Dataset 23 RF Multiclass-No SMOTE Random Forest(RF) with Multiclass feature configuration and No-SMOTE application to Dataset 24 RF Multiclass-SMOTE Random Forest(RF) with Multiclass feature configuration and with SMOTE application to Dataset

show abstract

“…In [13]- [15], several machine learning and deep learning models are used for mobile money SMS Fraud detection. Due to the lack of datasets, authors in [16] simulated mobile transfer fraud schemes to apply supervised learning to detect fraudulent transactions. Likewise, authors in [17] develop a community detection algorithm coupled with clustering on simulated data for mobile money fraud.…”

Section: Introductionmentioning

confidence: 99%

Characterizing Mobile Money Phishing Using Reinforcement Learning

Njoya,

Ngongag,

Tchakounté

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Mobile money helps people accumulate, send and receive money using their mobile phones without having a bank account (i.e., in some African countries). Such technology is heavily and efficiently used in many areas where bank services are unavailable and/or in crisis (i.e., during the Covid-19 pandemic) when transportation and services are limited. However, malicious users such as scammers have leveraged social engineering techniques to abuse mobile money services through scams, and frauds, among others. Existing countermeasures, which are specific to mobile money security, mostly ignore the dynamic aspect of interactions between the malicious party and the victim. Considering the above insufficiency, this paper proposes a new approach to characterize mobile money phishing attacks based on reinforcement learning (RL) through Q−learning and Markov decision processes (MDP) and on deep reinforcement learning (DRL) through DRL algorithms, namely, Deep sarsa, Advantage Actor-Critic (A2C), Deep Deterministic Policy Gradient (DDPG), and Deep Q-learning (DQN). In fact, the proposed approach models the optimal sequences of attacker actions to achieve their goals through reinforcement learning and deep reinforcement methods. We experiment on real attack scenarios that have been encountered at Orange and MTN telecoms. Furthermore, we compared reinforcement learning and deep reinforcement learning algorithms to each other and thereby demonstrated the difference between them. This analysis showed a better performance in learning with RL. We also deduced that Q− learning takes less execution time than CDM and therefore its learning quality is better for characterizing mobile money phishing attacks. Finally, we found that some deep reinforcement algorithms, such as Deep Sarsa and A2C, can improve the characterization of scammervictim interactions during mobile payments.

show abstract

Predicting Fraud in Mobile Money Transactions using Machine Learning: The Effects of Sampling Techniques on the Imbalanced Dataset

Cited by 5 publications

References 39 publications

Analyzing Adaptive and Non-Adaptive Online Learners on Imbalanced Evolving Streams

Analyzing Adaptive and Non-Adaptive Online Learners on Imbalanced Evolving Streams

Performance Evaluation of Machine Learning Models for Cyber Threat Detection and Prevention in Mobile Money Services

Characterizing Mobile Money Phishing Using Reinforcement Learning

Contact Info

Product

Resources

About