US-based multi-business firm that is a global leader in design, manufacture, and distribution of a wide range of agricultural equipment.
The client wanted to mitigate risks and vulnerable links in the supply chain. The client wanted to focus on top suppliers of agricultural sub-appliances. The client faced challenges in automating the data capture process and minimizing manual efforts.
SG Analytics created a model for risk estimation associated with each component delivery based on the need to maintain the flow of supply chain and to avoid surplus/shortage:
SG Analytics' team gathered data for various components of a given product type to be used as a demand value and in risk prediction in the supply chain.
Our data scientists developed the demand value of these components and the risk associated with their delivery.
Our team used attributes such as country, logistical, performance, supplier, and supply quantity as predictors.
We monitored the estimated value error continuously and improvised models for better results.
The team used techniques such as artificial neural network, linear regression, and support vector machine to estimate demand value, and predict risk probability as well as risk severity (High, Medium, Low).
Reduced risk of component shortage/ surplus by accurately forecasting demand values.
Enabled 25% cost savings from supply chain process optimization.
Ensured cross-utility and adaptability of the model for other inventory types across various products.
Calculated vendor ratings to gauge performance.