TSI logo 25 years
LV EN
Home > About Us > Structure and Government > Abstracts

DEGREE

PROGRAMME

FACULTY

YEAR

LANGUAGE

Boosting Algorithms for Credit Card Fraud Detection Across Varied Datasets

Manual reviews and rule-based systems, as well as data mining techniques such as clustering and classification algorithms, are crucial for identifying credit card fraud since they help identify fraudulent transactions. Despite obstacles in gathering training data, more data has lately been available, however, a complete comparison of current machine learning approaches has yet to be conducted. Algorithms like XGBoost, AdaBoost, and Gradient Boosting Machine frequently outperform older approaches. This study compares boosting algorithms to traditional approaches using three different credit card transaction datasets: synthetic, balanced with 50% fraudulent transactions, and very unbalanced with only 0.17% fraudulent transactions. The genuine transaction datasets contained 28 anonymized parameters such as time and location. Each method was evaluated using the F1 score, accuracy, precision, and recall. This study makes recommendations on which algorithms to use in real-world scenarios, giving important insights for future research and practical use in credit card fraud detection.

Author: Justs Vīdušs

Supervisor: Nadežda Spiridovska

Degree: Master

Year: 2024

Work Language: English

Study programme: Computer Sciences

More...

PREDICTIVE ANALYTICS FOR ONLINE CASINO REVENUE IN THE AUSTRALIAN MARKET.

This thesis investigates the influence of economic indicators and weather conditions on online slot machine gambling habits and revenues in Australia. By reviewing the interplay of GDP, CPI, and unemployment rates, the study uncovers their impact on gambling behaviors, revealing that a healthier economy boosts gambling expenditures while financial strain reduces participation. Weather's impact was minimal, likely due to the indoor nature of gambling. Predictive models, including Multiple Linear Regression, ARIMAX, and SARIMAX, were developed and evaluated. ARIMAX and SARIMAX models proved more accurate for predicting gross gaming revenue and winning bets, capturing seasonal and external influences effectively. This research provides insights for policymakers and industry stakeholders, emphasizing the need for localized studies to better understand these dynamics and improve strategic planning in the gambling sector. Future work should focus on expanding datasets and incorporating diverse economic and weather patterns to enhance predictive accuracy and industry applicability.

Author: Jānis Želannovs

Supervisor: Nadežda Spiridovska

Degree: Master

Year: 2024

Work Language: English

Study programme: Computer Sciences

More...

Table View
Text View