Fraud Detection in Mobile Payment Systems using an XGBoost-based Framework

2023 | Information Systems Frontiers | Citations: 0

Authors: Hajek, Petr; Abedin, Mohammad Zoynul; Sivarajah, Uthayasankar

Abstract: Mobile payment systems are becoming more popular due to the increase in the numb ... Expand

Abstract: Mobile payment systems are becoming more popular due to the increase in the number of smartphones, which, in turn, attracts the interest of fraudsters. Extant research has therefore developed various fraud detection methods using supervised machine learning. However, sufficient labeled data are rarely available and their detection performance is negatively affected by the extreme class imbalance in financial fraud data. The purpose of this study is to propose an XGBoost-based fraud detection framework while considering the financial consequences of fraud detection systems. The framework was empirically validated on a large dataset of more than 6 million mobile transactions. To demonstrate the effectiveness of the proposed framework, we conducted a comparative evaluation of existing machine learning methods designed for modeling imbalanced data and outlier detection. The results suggest that in terms of standard classification measures, the proposed semi-supervised ensemble model integrating multiple unsupervised outlier detection algorithms and an XGBoost classifier achieves the best results, while the highest cost savings can be achieved by combining random under-sampling and XGBoost methods. This study has therefore financial implications for organizations to make appropriate decisions regarding the implementation of effective fraud detection systems. Collapse

Topics: fraud detection mobile system mobile payment electronic payment Python

Methods: XGBoost machine learning anomaly detection supervised learning experiment

Improving debt collection via contact center information: A predictive analytics framework

2022 | Decision Support Systems | Citations: 0

Authors: Sánchez, Catalina; Maldonado, Sebastián; Vairetti, Carla

Abstract: Debt collection is a very important business application of predictive analytics ... Expand

Abstract: Debt collection is a very important business application of predictive analytics. This task consists of foreseeing repayment chances of late payers. In this sense, contact centers have a central role in debt collection since it improves profitability by turning monetary losses into a direct benefit to banks and other financial institutions. In this paper, we study the influence of contact center variables in predictive models for debt collection, which are combined with the financial information of late payers. We explore five different variants of three predictive analytics tasks: (1) the probability of successfully contacting a late payer, (2) the probability of achieving a contact that results in a promise to pay a debt, and (3) the probability that a defaulter repays his/her arrears. Four research questions are developed in the context of debt collection analytics and empirically discussed using data from a Chilean financial institution. Our results show the positive impact of the combination of the two data sources in terms of predictive performance, confirming that valuable information on late payers can be collected from contact centers. Collapse

Topics: decision making data integration analytical information system explainable artificial intelligence shapley additive explanation

Methods: machine learning decision tree classification case study feature engineering literature study

Analyzing the role of national culture on content creation and user engagement on Twitter: The case of Indian Premier League cricket franchises

2021 | International Journal of Information Management | Citations: 0

Authors: Deep Prakash, C.; Majumdar, Adrija

Abstract: The content generation strategy of a sports franchise determines whether the use ... Expand

Abstract: The content generation strategy of a sports franchise determines whether the user engagement increases or decreases on social media platforms. Thus, the role of Chief Operating Officer (COO) is profound who generally decides and governs social media policies of the franchises. We show that the cultural differences between localCOO vis-a`-vis foreign-COO-governed sports franchises reflect in their content generation strategy and are also associated with user engagement. We use Hofstede’s cultural dimensions theory and extract relevant features from the tweets. Overall, the results show that user engagement is more when the content generation strategy is in alignment with fans’ national culture. The first contribution of our work is towards showing the incremental impact of power distance, individualism and collectivism on user engagement. The second contribution of our work is towards feature construction, feature selection and building authorship attribution classifiers to un­ derstand the content generation strategy. Prior literature shows that national culture impacts writing of online reviews. We investigate the role of national culture in social media content generation and user engagement and extend the literature. Our study is useful for organizations to understand the role of national culture in content generation and how it is related to user engagement. Collapse

Topics: Twitter social media national culture Facebook Instagram

Methods: machine learning support vector machine robustness check random forest classification regression analysis method

Theories: cultural dimensions theory

Towards early purchase intention prediction in online session based retailing systems

2021 | Electronic Markets | Citations: 2

Authors: Esmeli, Ramazan; Bader-El-Den, Mohamed; Abdullahi, Hassana

Abstract: Purchase prediction has an important role for decision-makers in e-commerce to i ... Expand

Abstract: Purchase prediction has an important role for decision-makers in e-commerce to improve consumer experience, provide personalised recommendations and increase revenue. Many works investigated purchase prediction for session logs by analysing users’ behaviour to predict purchase intention after a session has ended. In most cases, e-shoppers prefer to be anonymous while browsing the websites and after a session has ended, identifying users and offering discounts can be challenging. Therefore, after a session ends, predicting purchase intention may not be useful for the e-commerce strategists. In this work, we propose and develop an early purchase prediction framework using advanced machine learning models to investigate how early purchase intention in an ongoing session can be predicted. Since users could be anonymous, this could help to give real-time offers and discounts before the session ends. We use dynamically created session features after each interaction in a session, and propose a utility scoring method to evaluate how early machine learning models can predict the probability of purchase intention. The proposed framework is validated with a real-world dataset. Computational experiments show machine learning models can identify purchase intention early with good performance in terms of Area Under Curve (AUC) score which shows success rate of machine learning models on early purchase prediction. Collapse

Topics: website electronic commerce anonymity marketing management user behavior

Methods: machine learning experiment computational algorithm literature study descriptive statistic

A prescriptive analytics framework for efficient E-commerce order delivery

2021 | Decision Support Systems | Citations: 0

Authors: Kandula, Shanthan; Krishnamoorthy, Srikumar; Roy, Debjit

Abstract: Achieving timely last-mile order delivery is often the most challenging part of ... Expand

Abstract: Achieving timely last-mile order delivery is often the most challenging part of an e-commerce order fulfillment. Effective management of last-mile operations can result in significant cost savings and lead to increased customer satisfaction. Currently, due to the lack of customer availability information, the schedules followed by delivery agents are optimized for the shortest tour distance. Therefore, orders are not delivered in customer-preferred time periods resulting in missed deliveries. Missed deliveries are undesirable since they incur additional costs. In this paper, we propose a decision support framework that is intended to improve delivery success rates while reducing delivery costs. Our framework generates delivery schedules by predicting the appropriate delivery time periods for order delivery. In particular, the proposed framework works in two stages. In the first stage, order delivery success for every order throughout the delivery shift is predicted using machine learning models. The predictions are used as an input for the optimization scheme, which generates delivery schedules in the second stage. The proposed framework is evaluated on two real-world datasets collected from a large e-commerce platform. The results indicate the effectiveness of the decision support framework in enabling savings of up to 10.2% in delivery costs when compared to the current industry practice. Collapse

Topics: decision support electronic commerce geographic information system logistics management decision support system

Methods: machine learning XGBoost simulation random forest classification computational algorithm

Bankruptcy prediction for SMEs using transactional data and two-stage multiobjective feature selection

2021 | Decision Support Systems | Citations: 0

Authors: Kou, Gang; Xu, Yong; Peng, Yi; Shen, Feng; Chen, Yang; Chang, Kun; Kou, Shaomin

Abstract: Many bankruptcy prediction models for small and medium-sized enterprises (SMEs) ... Expand

Abstract: Many bankruptcy prediction models for small and medium-sized enterprises (SMEs) are built using accountingbased financial ratios. This study proposes a bankruptcy prediction model for SMEs that uses transactional data and payment network–based variables under a scenario where no financial (accounting) data are required. Offline and online test results both confirmed the predictive capability and economic benefit of transactional data–based variables. However, incorporating those features in predictive models produces high dimensional problems, which deteriorates model interpretability and increases feature acquisition costs. Thus, we propose a two-stage multiobjective feature-selection method that optimizes the number of features as well as model classification performance. The results showed that the proposed model achieved similar classification perfor­ mance while greatly reducing the cardinality of the feature subset. Finally, the feature importance evaluation for features in the optimal subset confirmed the importance of transactional data and payment network-based variables for bankruptcy prediction. Collapse

Topics: permutation feature importance accounting information privacy law legal context decision making

Methods: machine learning computational algorithm experiment support vector machine decision tree classification

Who Is the Next “Wolf of Wall Street”? Detection of Financial Intermediary Misconduct

2020 | Journal of the Association for Information Systems | Citations: 0

Authors: Lausen, Jens; Clapham, Benjamin; Siering, Michael; Gomber, Peter

Abstract: Financial intermediaries are essential for investors’ participation in financial ... Expand

Abstract: Financial intermediaries are essential for investors’ participation in financial markets. Because of their position within the financial system, intermediaries who commit misconduct not only harm investors but also undermine trust in the financial system, which ultimately has a significant negative impact on the economy as a whole. Building upon information manipulation theory and warranting theory and making use of self-disclosed data with different levels of external verification, we propose different classifiers to automatically detect financial intermediary misconduct. In particular, we focus on self-disclosed information by financial intermediaries on the business network LinkedIn. We match user profiles with regulator-disclosed information and use these data for classifier training and evaluation. We find that self-disclosed information provides valuable input for detecting financial intermediary misconduct. In terms of external verification, our classifiers achieve the best predictive performance when also taking regulator-confirmed information into account. These results are supported by an economic evaluation. Our findings are highly relevant for both investors and regulators seeking to identify financial intermediary misconduct and thus contribute to the societal challenge of building and ensuring trust in the financial system. Collapse

Topics: LinkedIn website data breach social network fraud detection

Methods: machine learning support vector machine sensitivity analysis classification method McNemar's test

Theories: information manipulation theory interpersonal deception theory

An Ensemble of Ensembles Approach to Author Attribution for Internet Relay Chat Forensics

2020 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Shao, Sicong; Tunc, Cihan; Al-Shawi, Amany; Hariri, Salim

Abstract: With the advances in Internet technologies and services, social media has been g ... Expand

Abstract: With the advances in Internet technologies and services, social media has been gained extreme popularity, especially because these technologies provide potential anonymity, which in turn harbors hacker discussion forums, underground markets, dark web, and so on. Internet relay chat (IRC) is a real-time communication protocol actively used by cybercriminals for hacking, cracking, and carding. Hence, it is particularly urgent to identify the authors of threat messages and malicious activities in IRC. Unfortunately, author identification studies in IRC remain as an underexplored area. In this research, we perform novel IRC text feature extraction methods and propose the first author attribution version of the deep forest (DF) model that is an ensemble of ensembles that utilizes the fusion of ensemble learning techniques. Our approach is supported by autonomic IRC monitoring. Experiments show that our approach is highly effective for author attribution and attains high accuracy even when the number of candidates is large while training data is limited. Collapse

Topics: personality IT security social media data security anonymity

Methods: experiment support vector machine ensemble learning decision tree classification LightGBM

Theories: big five model

Feature Generation Using Machine Learning from Large Sparse Financial Data

2019 | Americas Conference on Information Systems | Citations: 0

Authors: Choi, Minjung

Abstract: The modeling of customer features has become a core component in modern financi ... Expand

Abstract: The modeling of customer features has become a core component in modern financial analytics. There are several difficulties in adopting conventional machine learning (ML) methodologies to finance domain: distributional asymmetry in the observations, class imbalance in the training labels, and data sparsity resulting from infrequent occurrence. In this study, we try to address the statistical challenges of financial data. Then, we test feature processing using multiple machine learning approaches in combination with established methods. We evaluate separate feature selection results as part of a prediction pipeline, and show how they differ across models. The empirical implications of the feature transformation and selection on the prediction outcomes are discussed. Collapse

Methods: data transformation experiment computational algorithm random forest classification principal component analysis

Business Analytics for Sales Pipeline Management in the Software Industry: A Machine Learning Perspective

2019 | HICSS | Citations: 0

Authors: Eitle, Verena; Buxmann, Peter

Abstract: This study proposes a model designed to help sales representatives in the softwa ... Expand

Abstract: This study proposes a model designed to help sales representatives in the software industry to manage the complex sales pipeline. By integrating business analytics in the form of machine learning into lead and opportunity management, data-driven qualification support reduces the high degree of arbitrariness caused by professional expertise and experiences. Through the case study of a software provider, we developed an artifact consisting of three models to map the end-to-end sales pipeline process using real business data from the company’s CRM system. The results show a superiority of the CatBoost and Random Forest algorithm over other supervised classifiers such as Support Vector Machine, XGBoost, and Decision Tree as the baseline. The study also reveals that the probability of either winning or losing a sales deal in the early lead stage is more difficult to predict than analyzing the lead and opportunity phases separately. Furthermore, an explanation functionality for individual predictions is provided. Collapse

Topics: enterprise information system marketing management customer relationship management system decision making analytical information system

Methods: machine learning support vector machine random forest classification computational algorithm XGBoost