BIA104 · AI-Assisted Analysis and Forecasting

Categories: Data & BI
Wishlist Share

About Course

Use AI assistants responsibly to speed up analysis, then build and test simple, explainable sales forecasts that a small business can actually use for planning.

Build · 6 hours · 4 lessons, a lab, an assessed assignment and a portfolio piece

Who it is for

Analysts, managers and owners who plan stock, staff or cash and want better forecasts without becoming data scientists.

Prerequisites

BIA103 or equivalent: comfortable with tidy data, KPIs and basic charts; no coding experience is required.

What you will be able to do

  • Use an AI assistant to explore data and draft analysis code while verifying every result.
  • Explain trend, seasonality and noise in a business time series.
  • Build baseline and exponential-smoothing forecasts and compare them with MAE and MAPE on a holdout period.
  • Present a forecast with a range and clear assumptions instead of a single number.

Lessons

  • Lesson 1 · AI assistants as analysis partners
  • Lesson 2 · Time series basics: trend, seasonality and noise
  • Lesson 3 · Exponential smoothing, backtesting and ranges
  • Lesson 4 · Lab and assignment

Lab: Forecasting weekly sales with a backtest

You will load two years of weekly sales for a sample garden center into Colab, ask an AI assistant to help you draft the exploration code, and check its output by hand. Then you will build a seasonal naive forecast and a Holt-Winters forecast, test both on the last 12 weeks and choose the better model with a forecast range.

Free tools: Google Colab (free) with pandas and statsmodels; optional free tier of an AI chat assistant

Assessed assignment

Forecast the next 12 weeks of a weekly business metric (sales, orders, bookings or similar) using real or sample data with at least 18 months of history. Compare at least two methods on a holdout period, report MAE and MAPE, and present the chosen forecast with an 80% range. Include a short log of how you used an AI assistant, one thing it got wrong or unclear, and how you verified it.

Criterion Weight What excellent work looks like
Data and exploration 20% The series is clean, gaps are handled, and trend and seasonality are described with a chart.
Method and backtest 35% At least two methods are compared fairly on the same holdout; error metrics are computed correctly.
Responsible AI use 20% The AI log is honest, sensitive data was not shared, and every AI-generated step was checked.
Communication 25% The forecast is shown with a range, assumptions and a recommendation that a manager can act on.

Portfolio piece

A Colab notebook and a one-page forecast summary showing method comparison, error metrics and a 12-week forecast with ranges.

Self-paced, 12-month access. Questions are answered in writing through the student panel. A completion record is issued when you finish the course.

Next step

Continue with BIA105 · Scenario Planning and Decision Models · 8 hours · $56.00

Continue to the next course

Prefer the whole program? Program in Business Intelligence & AI Decision Making · $277.00 (10% less than buying the courses separately)

Show More

What Will You Learn?

  • Use an AI assistant to explore data and draft analysis code while verifying every result.
  • Explain trend, seasonality and noise in a business time series.
  • Build baseline and exponential-smoothing forecasts and compare them with MAE and MAPE on a holdout period.
  • Present a forecast with a range and clear assumptions instead of a single number.

Course Content

BIA104 · AI-Assisted Analysis and Forecasting (6 h)
Use AI assistants responsibly to speed up analysis, then build and test simple, explainable sales forecasts that a small business can actually use for planning.

  • Lesson 1 · AI assistants as analysis partners
  • Lesson 2 · Time series basics: trend, seasonality and noise
  • Lesson 3 · Exponential smoothing, backtesting and ranges
  • Lesson 4 · Lab and assignment
  • BIA104 Assessment · AI-Assisted Analysis and Forecasting
Scroll to Top