Build and compare statistical and machine-learning forecasts for demand and market-style data without treating them as guaranteed trading signals. 1. Who can join Suitable for: Data scientists, finance analysts and forecasting professionals Mandatory prerequisites: Python, statistics and model evaluation; familiarity with time-series data helpful 2. Duration 48 live hours • Approximately 8 weeks at 6 hours per week; actual timetable to be confirmed. 3. Mode Classroom - Thaiyur / Kelambakkam, OMR Chennai (subject to schedule) Live Online (subject to schedule)
4. Syllabus — five modules
Module 1: Time Series Fundamentals: Stationarity, Autocorrelation & Seasonality Learning outcome: Identify trends, seasonality and stationarity in time-series datasets. Module 2: Statistical Models: ARIMA, SARIMAX & Exponential Smoothing Learning outcome: Fit and validate ARIMA-style and smoothing baselines. Module 3: Modern Forecasting at Scale: Meta Prophet & NeuralProphet Learning outcome: Compare Prophet-family forecasting approaches. Module 4: Deep Learning for Sequences: LSTMs, GRUs & Temporal Fusion Transformers Learning outcome: Demonstrate neural sequence forecasting on a contained example. Module 5: Portfolio Optimization, Risk Management Metrics & Algorithmic Signals Learning outcome: Report backtesting performance and discuss risk constraints. 5. Practical project Source capstone title: Build an Automated Financial Market & Demand Forecasting Engine Student deliverable: A forecasting application that loads historical data, creates backtested forecasts, visualizes uncertainty and compares model errors.
6. What is included Live trainer-led sessions Practical assignments Sample code or templates, as applicable Project feedback Learning assessment Perizona course-completion certificate subject to assessment 7. Upcoming batch Start date: To be announced. Students can register interest; dates are shared only after confirmation.
