AI for Supply Chain and Planning is a course in using AI for supply chain planning, from seasonal demand forecasting in Excel and Python and measuring accuracy with MAPE to safety stock, reorder points, MPS, MRP and S&OP scenarios. It suits production planners, purchasing teams and warehouse and logistics staff, and you leave able to build a supply chain KPI dashboard in Power BI.
Manufacturers facing seasonal demand have to plan under several layers of uncertainty at once: sales that rise and fall through the year, raw material prices, delivery lead times and supplier risk. Planning on experience and spreadsheets alone risks both excess inventory and stockouts in the busiest season, so planning teams need tools that forecast more accurately and support faster decisions. This course applies AI across the Plan, Source, Make, Deliver cycle. It starts with forecasting seasonal demand using Forecast Sheet (ETS) and Python in Excel, measuring accuracy with MAPE and forecast bias, and building a
consensus forecast. It then turns the forecast into inventory policy with ABC / XYZ, safety stock and reorder point, plans production with MPS, MRP and capacity planning concepts, uses Copilot for procurement work, builds a supply chain dashboard in Power BI, and closes with scenario simulation for an S&OP meeting. Every step is hands-on in Excel, Copilot and Power BI on simulated data that runs continuously across both days. This is not ERP or planning software training, and no programming is required. (2 days, 6 hours per day, 12 hours in total, Intermediate level.)
Course Details
A 2-day course, 6 hours per day (12 hours in total, 09:00-16:00), delivered as lectures with hands-on workshops built on one continuous case across both days. Intermediate level, no programming required. The course focuses on applying AI with the tools planning teams already use; it is not ERP or planning software training. Tools covered are Microsoft Excel (Forecast Sheet, PivotTable) with Copilot and Python in Excel, Power BI Desktop and Microsoft 365 Copilot Chat. Learners bring a Windows 10/11 notebook with current Microsoft 365 Apps and Power BI Desktop installed in advance, plus a Microsoft 365 Copilot account as enabled by their organization. Practice
data covering sales history, inventory, lead times and suppliers is simulated with seasonal patterns and provided by the instructor, and learners may bring their own masked data to the workshops. Learners take home a demand forecasting Excel file with accuracy measurement, an ABC / XYZ, safety stock and reorder point template, a prototype Power BI dashboard for supply chain KPIs, prompt templates for procurement and supplier analysis, and S&OP recommendation slides from the scenario simulation. Assessment includes a 20-question pre-test and post-test, evaluation of forecast and calculation accuracy in the workshops and the quality of the S&OP presentation, and a post-training satisfaction survey.
Section 1: The Supply Chain in the AI Era
Section 2: AI Use Cases Across the Supply Chain
Section 3: Demand Forecasting Fundamentals
Section 4: Hands-On Forecasting in Excel
Section 5: Forecast with Data, Decide with People
Section 6: Workshop 1: Seasonal Demand Forecast
Section 7: Inventory Management with AI
Section 8: Production and Capacity Planning
Section 9: AI for Procurement
Section 10: Supply Chain Dashboard
Section 11: Limitations and Risks of AI
Section 12: Workshop 2: S&OP Scenario
No public rounds are open right now. Join the waiting list and we will contact you first when the next round opens, or ask us on LINE. Or call 02-570-8449 or 088-807-9770
A common formula sets safety stock as the Z value for your target service level multiplied by the standard deviation of daily demand and by the square root of the lead time in days. The reorder point is average daily demand multiplied by the lead time, plus safety stock; when stock falls to that level, you place an order. The more volatile the demand or the less reliable the lead time, the higher the safety stock needs to be.
MAPE, or mean absolute percentage error, is the average percentage gap between forecast and actual demand, ignoring whether the error is positive or negative. Lower is better, but it does not show direction, so pair it with forecast bias, which reveals whether you consistently over- or under-forecast. Be careful with items whose actual sales are zero or very low, as MAPE becomes unreliable there.
Start by arranging the data in two columns: evenly spaced dates or months, and the sales for each period. Then select the data and use Forecast Sheet on the Data tab, which applies exponential triple smoothing and detects seasonality automatically. Set the forecast end date and confidence interval, and finally compare the results with actual sales using MAPE to decide whether the method needs adjusting.
It suits production planning staff and supervisors, procurement and supplier management teams, warehouse and logistics staff, and anyone who takes part in S&OP meetings. You should have completed AI Literacy for Everyone or understand basic AI concepts, know the planning, purchasing or warehouse work of your own unit and use Excel at an intermediate level, including basic formulas and PivotTables. No programming or advanced statistics is required.
You will be able to forecast seasonal demand with Forecast Sheet, Copilot and Python in Excel and measure accuracy with MAPE, classify items with ABC/XYZ analysis, calculate safety stock and reorder points, run what-if scenarios to prepare for S&OP meetings and build a supply chain KPI dashboard in Power BI. Participants who complete the training receive a Certificate of Completion with its own number, which can be verified online.
Bring a Windows 10 or 11 laptop with current Microsoft 365 Apps and Power BI Desktop installed in advance, plus a Microsoft 365 Copilot account if your organisation provides one. Practice data is simulated with seasonal patterns and supplied for you, and you may bring your own masked data to the workshop. The course does not teach any particular ERP or planning system.
Factories and manufacturing work are full of documents, data and routine tasks: creating and improving SOPs and work instructions, recording and analyzing production data, finding the causes of defects and downtime, preparing shift and monthly reports,…
AI is only as smart as the data it is fed. Many AI projects fail not because of the technology but because data is scattered across many places, product or vendor codes do not match between systems, records are incomplete, or no one clearly owns the data. At…
Many organizations start AI projects with real enthusiasm, yet a good number get stuck in pilots that never finish, known as pilot purgatory, because the problem was never clearly defined, the data was not there to support it, nobody owned the project,…
