About Embedded Machine Learning

Machine Learning (ML) which is a form of artificial intelligence (AI) can help with you make better planning decisions. Machine learning uses data and algorithms to enable systems to learn and improve in a manner similar to humans. Predicting shipment transit times and order routes can be a challenge in today's ever changing environment.

Embedded Machine Learning (EML) allows you to use historical data to predict end-to-end transit times for direct shipments and to predict order routes. EML leverages OTM historical shipment and order data with optimized algorithms and machine learning techniques to deliver highly accurate predictions. For more accurate predictions, you should use a large number of shipments and lanes. You can also use EML in GTM to predict item product classifications.

Note: Machine learning requires a large amount of input data to produce accurate results. See Configuring Machine Learning: Transit Time Prediction and Configuring Machine Learning: Product Classification Prediction

EML can be used to predict OTM shipment transit times, OTM order routes, and GTM item product classifications. These are continuous processes in which the information gained from the results of machine learning training is used to both make changes to current process and to update setup data that can then be used to enhance machine learning model training.

Let's review the EML high-level flow:

1. Data Setup: Machine learning needs data as input. The more input data the better. LML provides historical OTM data via machine learning projects and machine learning scenarios. This data can include shipment and tracking event data, orders, or GTM items and related data.
2. Data Export and Pre-Training Analytics: Export this historical data to Oracle Transportation Intelligence (OTI) and review it to see if you want to change the data setup.
3. Training and Post-Training Analytics: Send machine learning scenario data to the embedded Oracle Machine Learning database for training. Then, review the learning results.
4. Prediction:
   • Select groups of OTM shipments and obtain a predicted transit time for each shipment.
   • Select OTM orders and obtain a predicted order route.
   • Select GTM items and obtain predicted classifications.
5. Evaluation: Finally, you evaluate all of this data. Set up OTM process management to automate the above steps.