Cargill provides food, agriculture, financial and industrial products and services to the world. In Asia Pacific, Singapore serves as its regional hub. Another business headquartered in Singapore is their metals business which focuses on helping miners, steel mills and end users manage volatility and increase profitability through tailored physical supply and financial solutions.
Through discussions with the metals team, it was highlighted that mitigating market volatility and minimising credit default is a critical objective.
To achieve this objective, it is important to monitor key risk indicators and identify risky counterparties. Doing so in a timely fashion presented a challenge given the volume of data that needed to be analysed and the fact that the data were organised in silos. NCS solved this business problem by designing and implementing an optimal data architecture and delivering insights using predictive analytics and advanced data visualisation.
NCS helped Cargill establish a strong analytics foundation by automating the calculation and ingestion of critical credit intelligence data into a central data platform called Cargill Data Platform (CDP). The fully automated process helped Cargill save significant manpower in manual computation and allowed the team’s credit analysts to focus on monitoring the business and making sound judgement calls. To rationalise and understand the complex and diverse set of credit intelligence data, NCS conducted a Business Process Review (BPR) to establish a logical mapping of the credit risk evaluation process to the company’s data value chain. This BPR exercise helped Cargill clarify how to best harness their data to satisfy the business objectives of the CDP.
In addition, NCS designed a set of intuitive and interactive dashboards that delivered actionable insights to enterprise stakeholders effectively. NCS developed Machine Learning algorithms that leveraged on existing credit intelligence data to predict the credit risk of counterparties. This predictive capability is critical for Cargill in limiting its risks and exposure to different tiers of counterparties, thereby limiting potential losses when experiencing periods of high volatility in the commodities market.
Throughout our development process, we adopted an agile approach where proof-of-concepts were developed and enhanced iteratively to ensure tight alignment between analytics outcomes and business goals.
As a result of this project, by adopting an AI and data-driven approach, Cargill is now better equipped to effectively minimise credit default risks and is able to reduce the number of instances of credit default and mitigate the impact of such default.