AI in Supply Chain and Economics of Logistics - Frank Corrigan
Francis Corrigan is Director of Decision Intelligence at Target Corporation. Embedded within the Global Supply Chain, Decision Intelligence combines data science with model thinking to help decision-makers solve problems. 00:00 Intro 01:21 Data Science applications in Logistics and Supply Chain, Cost and Performance trade-off 03:21 Amazon vs Target fulfillment Model, Owning vs Coordinating with Last Mile companies e.g. FedEx 08:36 Suez Canal Container Blockage, Fallback plan at Target 10:37 Predicting products to Stock in Bottle Neck Scenarios 12:42 Air Freight vs Sea Shipments Costs, Ideal vs Real World Deliveries 15:48 Lack of Good Data and Prediction Challenges 18:00 Managing Expectations as Head of Analytics, Importance of Communicating 20:11 Stakeholder Management & Data Science Newsletter 23:39 Technical and Non-technical Teams Coordination, Speed Reading 26:36 Data Stories and Visualizations 29:47 Reporting Pipelines vs Story Narration 31:37 Times Series, Prophet, Flourish and Hans Rosling 35:28 Economist turned Data Scientist, Embarrassment as Motivation 38:20 Lack of Practical Skills of Data Science at University 41:18 Employer’s Perspectives on Data Science Talent 45:24 What Causes Data Teams Failure 48:40 COVID 19 and Times Series Corruption, Anomaly Detection 56:15 Toilet Paper Demand Scenario, Commodity Pricing Alerts 59:50 Automating Alerts for Panic Situation 01:02:10 Pandemic as a Blessing for Digital Business, Exponential Growth Rates and Tuition Fee Reimbursement for Employees 01:06:06 Data as Decision Support System, Strategic Decision Indicators 01:08:08 Capital in 21st Century, Thomas Piketty and Free Markets 01:11:31 Failures of Capitalist Societies on Individual Front and Socialist Aversion of Wealth Generation 01:15:15 UBI, Interventions, and CEO to Lowest Paid Worker Ratio 01:18:25 Career Blunders and Regrets 01:22:12 Psychometric Tests for Intellect Filtering, Behavioral Stability and Creativity Trade-off 01:24:08 Target’s Epic Failure in Canada, What Data Science could have Prevented 01:25:08 Gameplan to Compete with Walmart and Amazon 01:28:00 Sarimax, Armiax and Volatility Management, Planning vs Forecasting 01:31:33 Deep NNs or Lack thereof, Explainability and Monte Carlo as Alternative 01:34:00 Model Parsimony in Times Series, Baseline Models in Excel 01:37:50 R vs Python, Specific Use Cases 01:40:25 Delegating and Element of Trust 01:43:20 Time and Space Complexity of Models, Netflix and Deployments at Target 01:46:00 Political Impacts on Shipments, Narratives and Hypothesis Testing 01:48:00 Nate Silver, Nassem Talib, and Early Inspirations 01:52:05 Work-life Balance