The problem of money laundering has significantly impacted Nigeria's economy, with the rise of cryptocurrency exacerbating financial crimes like terrorism financing. To address this, a project aimed to develop a machine learning model to detect money laundering in bitcoin transactions using blockchain security technology. The dataset, consisting of 2,906 entries from Kaggle, was split into 70% for training and 30% for testing. Cross-validation trials were also conducted. The k-means clustering algorithm, an unsupervised learning technique, was used to group the data, and the K-Nearest Neighbour (KNN) classifier labeled these clusters. The model predicted bitcoin laundering based on these labeled samples, leveraging blockchain's data immutability through consensus mechanisms and cryptographic principles. Experimental results showed that the algorithm accurately identified 87.2% of legitimate transactions and 12.6% of money laundering operations, with a very low misclassification rate of 0.002%. The model achieved 95% accuracy, 97% precision, and 100% recall using the percentage split approach. Additionally, a 5-fold cross-validation yielded a mean accuracy score of 99%, indicating the model's robustness and reliability without overfitting or underfitting. In summary, the model demonstrated high reliability, accurately distinguishing between legitimate and illicit bitcoin transactions with minimal error.

Money laundering bitcoin transactions financial crimes blockchain crypto currency