Technician dispatching not as efficient as possible
Currently used algorithms were too slow and did not allow for quick reaction, recalculation of the routes/dispatching of the technicians
Solution
Train a reinforcement learning model to achieve same or better accuracy more quickly at a lower cost
Impact
Improved Technician efficiency, reaching more customers and resolving more issues per technician per day
Aviation data platform
Customer
Airplane producer
Problem
The customer was creating an industry leading airplane data platform
Data from 100s of global airlines needed to be integrated on a single platform to allow predictive maintenance.
Solution
Unit8 team helped with onboarding maintenance data from airlines in order to create data ecosystem accessible to airlines and manufacturers
Impact
Unit8 contributed to the creation of the data platform allowing the customer to gain deeper visibility into the airplane data
New level of insights for predictive maintenance
Airline onboarding to a data platform
Customer
Airplane producer
Problem
Upon creation of the data platform for airplane maintenance, the customer wanted to connect different airlines to the platform
Solution
Unit8 helped onboard several airlines onto the common aviation platform to exchange airplane maintenance data
Impact
Customer gets more granular visibility into the airplane mechanics and operations
New level of insights for predictive maintenance
AI Supply Chain Forecasting
Customer
Major Swiss Chemical company
Problem
The need to improve the current forecasting process (raw-materials, finished goods and sales)
Solution
New approach to improve forecasting quality and the effort needed to maintain it using new data sources like Forward looking indicators, Financial metrics: (GDP, Inflation, FX rates) and Big events (e.g. new years in china, olympic games etc.)
Impact
Automation -> less manual work, less errors, less time
Higher accuracy (97-98%)
Better planning/cost savings
AI Sales Forecasting
Customer
Major Swiss Chemical company
Problem
The customer was looking to automate the sales forecasting process which to date was performed in a manual way, making it cumbersome and error prone
Solution
New approach to improve forecasting quality and the effort needed to maintain it using new data sources like Forward looking indicators, Financial metrics: (GDP, Inflation, FX rates) and Big events (e.g. new years in china, olympic games etc.)
Impact
Automation -> less manual work, less errors, less time