Grab’s existing process to mitigate & detect ML transactions is labour intensive. The team was tasked to develop an automated solution that minimizes manual involvement and enhances effectiveness of anomaly detection. They adopted a data-driven approach to identify transactions with the highest risk of ML activity.
The team was tasked to enhance and streamline Grab's Anti-Money Laundering (AML) process, by developing an efficient and automated solution to mitigate risks. The team adopted the following approach: from data preparation to unsupervised learning to rule-based filtering and supervised learning and finally dashboard development.
The team was tasked to enhance sales performance and drive informed business decisions, by enabling Far East Flora’s management to understand and leverage data from its ERP system to monitor key sales metrics and customer buying trends.
The team proposed new analyses to address the outdated data utilisation practices which resulted in restricted business understanding at Far East Flora Market. The team offered RFM Analysis to identify customers who showed changes in purchasing behaviour to implement targeted marketing to retain customer base and other solutions.
