An Early Warning System based on Logistic Regression was created to predict downtime in processing line for a leading snack foods company. This resulted in $2 million savings in cost per fryer and potential save of $50 million after rollout to 30 plants across the US.
A Machine Learning Rules & Notification engine was built for a leading transnational consumer goods company, which helped make timely market interventions in supply chain planning, reducing the stock-out rate by 5% and inventory costs by 2%.
For a leading global technology infrastructure provider, regularized random forests and ‘SVD + Univariate Forecasts’ were combined to improve forecast accuracy, enabling potential savings between $3 million -$5 million.
Baseline forecasts for 3000 SKU’s were generated for the world’s third-largest jewelry manufacturer. New SKUs were automated. This led to a 13% increase in overall demand forecast accuracy and reduced supply planning costs by 2%.
A data ecosystem from multiple disjointed unstructured and structured data sources was built for the world’s largest entertainment production company, which resulted in a savings of half a million dollars per year from revenue leaks.
Combined forecasts from different algorithms were done to improve demand forecasting accuracy for a leading home appliances and repair services provider. Demand forecasting accuracy went up to 92% from 65%, reducing lead time by 20%. A 4% increase in First Time Completes resulted in incremental revenue of $5 million per annum due to reduced cancellations.
Process Mining was used to identify bottlenecks for a leading snack and beverage manufacturer, which resulted in savings of $1 million per packaging line.
A reliable, automated forecasting system was built for a PC, imaging, and printing products provider, which resulted in 8x faster computation and a 5x reduction in infrastructure cost.
