Generative AI In Logistics_Object Automation
- 1. Generative AI In Logistics Sivakumar Shanmugam Werner WERNER
- 2. AGENDA •About Werner •AI vs ML vs DL vs Generative AI •Machine Learning Types / Steps •Traditional Vs In Database ML •Supporting Databases •Deep Dive into Machine Learning on Db2 Platform •DEMO : TRUCK (SENSOR DATA) / (Using Naive Bayes classification algorithm) •WHAT IS NEXT ?
- 3. ABOUT WERNER Largest Carrier in Midwest America – Head Quarters –Omaha, NE Operates Across USA / Canada & Mexico
- 5. Werner Tractor Locations – Tractor Ping Data (8000 Trucks / 35,000 Trailers)
- 6. Werner Logistics - Company info •Werner Revenue is at $ 3.3 Billions = 25,000 Crores Rs Rupees • Our plan is to reach $ 5 Billion = 40,0000 Crore RS by the end of 2025 -
- 7. What are the paths we are taking •Moving from On-prem to Cloud Architecture Master Mind – New cloud based TMS system Sales force - Stores Pricing & Sales information Work day - Stores Company Employee info Snowflake - Cloud base data Warehousing, Azure(Sqldb/cosmosdb) - Stores inhouse developed Application data. Chat GPT , Bing/ Copilot, ChatBot are going to play a crucial role during the development and data integration process.
- 8. …Paths we are taking •Autonomous Trucking – Driver will be still on the seat. •Employees (2500) , Drivers (10000) – Employee to Driver Ratio 1:4 • According to the USA bureau of Labor Statistics Employment rate for data scientist will grow by 36 % in next 5 years.
- 9. AI vs ML vs DL vs Gen AI
- 11. Machine Learning Vs Generative AI Bart / Gemini – Recognizes images
- 12. Generative AI in Logistics
- 13. IN-DATABASE MACHINE LEARNING SIMPLE SETUP
- 14. Deep Dive into Machine Learning on Db2 Platform
- 15. dB2 V11.5.4 (in-database Machine learning)
- 17. DATABASE SETUP Install & setup Db2 V 11.5 fp 5 on Linux Environment
- 19. COLLECT DATA Data feed from Trucks to Databases IBM DB2 V 11.5.6 database
- 20. LINK DEMO 1 - PREDICTIVE MAINTENANCE OPTIMIZATION OF TRUCK FLEET DATA SET
- 23. Opportunities for predictive Modeling How long the truck can run without maintenance ? How many drivers can quit in the next 30 days ? Company turnover in future ? Accident Prevention ? Battery life on the trucks ? Weather alerts to drivers - k-means algorithm? Run machine learning set up on AIX-Open shift environment (Testing in progress)
- 24. STEP 2 : Data transformation • Use the following stored procedures to transform the data before passing it to a machine learning algorithm. IDAX.IMPUTE_DATA - Impute missing data IDAX.SPLIT_DATA - Split data into training data and test data IDAX.STD_NORM - Standardize or normalize columns of the input table IDAX.EFDISC - Discretization bins of equal frequency IDAX.APPLY_DISC - Discretize data by using limits for discretization bins
- 25. STEP 3. Data exploration Use these stored procedures to evaluate the content of the given data IDAX.SUMMARY1000 - Summary of up to 1000 columns IDAX.COLUMN_PROPERTIES - Create a column properties table IDAX.GET_COLUMN_LIST - Get a list of columns
- 26. STEP 4 : Model building •Use these stored procedures to build machine learning models. Decision trees - IDAX.GROW_DECTREE A decision tree is a hierarchical, graphical structure accurately classify a model. Linear regression - IDAX.LINEAR_REGRESSION is the most commonly used method of predictive analysis. Naive Bayes IDAX.NAIVEBAYES - The Naive Bayes classification algorithm is a probabilistic classifier. K-means clustering IDAX.KMEANS - The K-means algorithm is the most widely used clustering algorithm
- 27. STEP 4 : Model tuning •Use these stored procedures to fine-tune your machine learning models IDAX.PRUNE_DECTREE - Prune a decision tree model
- 28. Step 5 : Model evaluation •Use these stored procedures to evaluate the performance of your model by comparing predictions to the true values. IDAX.CMATRIX_STATS - Calculate classification quality factors from a confusion matrix IDAX.CONFUSION_MATRIX - Build a confusion matrix IDAX.MAE - Calculate the mean absolute error of regression predictions IDAX.MSE - Calculate the mean squared error of regression predictions
- 29. STEP 6 Model inferencing/ Deployment •Use these stored procedures to make predictions with your trained machine learning model. IDAX.PREDICT_DECTREE - Apply a decision tree model IDAX.PREDICT_KMEANS - Apply a K-means clustering model to new data IDAX.PREDICT_LINEAR_REGRESSION - Apply a linear regression model to a target IDAX.PREDICT_NAIVEBAYES - Apply a Naive Bayes model to new data
- 30. Model management •Use these stored procedures to clean up obsolete models and tables. IDAX.DROP_SUMMARY1000 - Drop output tables created by SUMMARY1000 IDAX.DROP_MODEL - Drop a model call IDAX.DROP_MODEL ('model=FLEET_LINEAR_REGRESSION_MODEL')
- 32. Ending with Steve Job’s Story – Stay hungry, Stay foolish •Born for Graduate School Mom and immediatley given for Adoption •College life •Fired from the company he started – Apple – Went on to start Next & later returned back to Apple later •If today were the last day of my life, would I want to do what I am about to do today?
- 33. THANKS