omomehinvictor/Fraud_Detection_Machine_Learning

We built machine learning models to predict if a Transaction in African Custom Service is Fraud or Not # Detecting Fraud in African custom service using Machine learning algorithms. The increasing amounts of imports and exports have served good purpose in many African countries and as well as avenue for fraud criminals to carry out their illicit acts in form of tax evasion, smugglings, money laundering, drugs trafficking etc. These very acts made it paramount for the government to find automatic or semi-automatic solutions to guide the customs’ activities in order to minimize the number of manual inspection of imports. In this notebook we use various machine learning techniques to detect if a transaction in a Africa custom service is fraud or not via Python implementation. ### Contents (1) Basic Preprocessing. (2) Exploratory Data Analysis. (3) Features Engineering. (4) Features Selectons. (5) Fix class Imbalance Problem (Random Oversampling). (5) Building & Evaluate Machine learning Models. (6) Best mMdel Selection (Cross Validation).