Data Science & AIMachine LearningIntermediate

Forecasting and Time Series with Python

ARIMA, Prophet, and practical forecasting for business.

4.8 (67) 44 lessons · 5 modules 14h420 studentsLanguage: English

Taught by

Meera Krishnan

Principal Data Scientist at Swiggy · Bengaluru

What you’ll learn

  • Decomposing and understanding time series data
  • ARIMA and when it is the right choice
  • Prophet for business forecasts with seasonality
  • Evaluating forecast accuracy honestly
  • Building a forecasting pipeline for business demand

About this course

A focused course on time series forecasting for business. We cover the fundamental models, when to use each, and how to evaluate forecasts honestly — not just on aggregate metrics but on the decisions they drive. Includes a real demand forecasting project.

Curriculum

5 modules · 44 lessons · 14h

1

Time series fundamentals

2 lessons

Trend, seasonality, and stationarity.

  • Decomposing a time seriesPreview16 min
  • Stationarity and differencing18 min
2

Practical forecasting models

2 lessons

ARIMA, Prophet, and when to use each.

  • ARIMA from scratch25 min
  • Prophet for business forecasts20 min

Requirements

  • Python and Pandas fluency
  • Basic statistics (mean, variance, distributions)

Who this course is for

  • Analysts building business forecasts
  • Data scientists working on demand or revenue prediction
  • Anyone who has been asked to “forecast next quarter”

Your tutor

Meera Krishnan

Principal Data Scientist at Swiggy · Bengaluru

4.9 (156)1.8k students2 courses

ML practitioner focused on recommendation systems and forecasting. Built Swiggy’s delivery-time prediction model and the menu ranking system. Teaches ML with a strong emphasis on production realities — drift, monitoring, and the boring parts that actually matter.

Student reviews

4.8

67 ratings

5
78%
4
16%
3
4%
2
1%
1
1%

Tarun Reddy

22 Jul 2024

12 found this helpful

Solid and practical

Good balance of theory and practice. The Prophet module was particularly useful for our retail demand planning.

Frequently asked questions

Do I need to know deep learning?
No. This course covers classical and practical methods. Deep learning for time series is a separate topic.