Search Results

Now showing 1 - 2 of 2

Credit Card Fraud Detection Analysis and Machine Learning Application
(MEF Üniversitesi, Fen Bilimleri Enstitüsü, 2018) Meker, Tuğrul; Özlük, Özgür
Credit card fraud transaction is a common term for theft and fraud action involving a payment card such as payment or credit card or debit card as a source of funds in transactions. With increased usage of POS channel or internet in recent years, the risks of credit card fraud have increased. Mostly, these illegal activities start with a compromise of data associated with the account number or important information that required to start the financial transaction. After, literature review and exploratory data analysis, machine learning algorithms are going to use to decide whether the transaction is fraud or not. Logistic regression, decision tree, Naive-Bayes, decision forest and linear SVC’s classifier algorithms are used in this study. With re-sampling choices (random-under, random-over sampling & SMOTE), these algorithms’ performances are compared. Logistic regression, decision tree, and random forest provide best results in terms of accuracy metrics. Grid-Search is applied to those three algorithms. Decision tree algorithm is chosen as the best algorithm for credit card fraud detection. Python 3.7 is used in this study.
Credit Card Churn Prediction With Machine Learning Algorithms
(MEF Üniversitesi, Fen Bilimleri Enstitüsü, 2018) Konuksal, Serap; Ağralı, Semra
Credit card is one of the main products in banking sector and there is a big competition in credit card business. This competition makes retention of customers critical. To retain the customers, it is very important to interpret the customers that may churn. Targeting right customers with right offer is the main aim of Customer Relationship Management (CRM) in marketing. When the churn probability of customers is predicted, it is easier to retain the customers by proposing the retention offers directly to the ones with high churn probability. This will allow banks to manage their marketing budgets efficiently. In this project, a private bank’s credit card customer data is used. Data includes many different types of features of customers, such as number and type of transactions, credit card limits, feature usage, credit bureau information and demographic information. We develop a set of churn prediction models by implementing different machine learning algorithms. We compare these algorithms to find the best model with highest accuracy to be offered to the bank. We also share the main indicators that affect churn so that the bank can use them in retention activities.

Yüksek Lisans Tezleri

Browse

Filters

Settings

Sort By

Results per page

Search Results