Time Series Forecasting with Machine Learning Training Course

Module 1: Foundations of Time Series Analysis

• Defining the unique properties of time series: Autocorrelation and Stationarity
• Understanding the four components: Trend, Seasonality, Cyclicity, and Noise
• Statistical testing for stationarity using the Augmented Dickey-Fuller (ADF) test
• Techniques for seasonal decomposition: Additive vs. Multiplicative models
• Visualizing temporal patterns using ACF (Autocorrelation) and PACF plots
• Practical session: Performing a complete exploratory data analysis (EDA) on a 10-year stock price dataset

Module 2: Feature Engineering for Temporal Data

• Creating lag features and rolling window statistics to capture historical dependencies
• Extracting date-time features: Day of week, month, holidays, and business cycles
• Handling missing values and outliers in time series without breaking temporal order
• Transformations and scaling: Log transforms, Differencing, and Box-Cox methods
• Identifying and integrating exogenous variables (covariates) to improve model power
• Practical session: Building a feature engineering pipeline to prepare raw sensor data for modeling

Module 3: Classical Statistical Forecasting Models

• Theoretical foundations of the Autoregressive (AR) and Moving Average (MA) models
• Implementing ARIMA (Autoregressive Integrated Moving Average) for non-stationary data
• Extending models to capture seasonality using the SARIMA framework
• Parameter selection and optimization using AIC/BIC criteria and grid search
• Understanding the limitations of linear statistical models in high-volatility environments
• Practical session: Fitting and tuning a SARIMA model to forecast monthly electricity consumption

Module 4: Smoothing Techniques and State Space Models

• Simple Exponential Smoothing for data without trend or seasonality
• Holt’s Linear Trend Method for capturing directional data movements
• Holt-Winters Triple Exponential Smoothing for complex seasonal patterns
• Introduction to Structural Time Series and Unobserved Components Models (UCM)
• Comparing smoothing methods against ARIMA-based approaches
• Practical session: Applying the Holt-Winters method to forecast airline passenger traffic

Module 5: Machine Learning for Regression-Based Forecasting

• Re-framing time series forecasting as a Supervised Learning problem
• Implementing Linear Regression and Lasso/Ridge for baseline temporal predictions
• Understanding the "Data Leakage" trap in time series machine learning
• Support Vector Regression (SVR) for capturing non-linear temporal relationships
• Analyzing the impact of feature selection on long-term vs. short-term forecasts
• Practical session: Building a regression-based model to predict daily retail sales volume

Module 6: Advanced Ensemble Methods in Time Series

• Using Random Forests to handle high-dimensional exogenous data
• Gradient Boosting Machines: Implementing XGBoost and LightGBM for forecasting
• Advanced hyperparameter tuning for tree-based models on temporal data
• Handling multi-step ahead forecasting: Recursive vs. Direct strategies
• Feature importance analysis to determine key drivers of the forecast
• Practical session: Developing a competitive XGBoost model for a demand forecasting competition dataset

Module 7: Forecasting with Facebook Prophet

• Introduction to the Prophet library: Robustness to missing data and trend shifts
• Configuring growth parameters: Linear vs. Logistic growth for market saturation
• Handling special events: Adding custom holiday effects and seasonalities
• Interpretable components: Extracting and visualizing trend and holiday effects
• Fine-tuning changepoint prior scale for flexibility in trend detection
• Practical session: Deploying a Prophet model to forecast website traffic with holiday adjustments

Module 8: Neural Networks for Sequence Prediction

• Introduction to Recurrent Neural Networks (RNNs) and their memory limitations
• Implementing Long Short-Term Memory (LSTM) networks for long-range dependencies
• Gated Recurrent Units (GRU) as a computationally efficient alternative to LSTMs
• 1D Convolutional Neural Networks (CNNs) for extracting local temporal patterns
• Hybrid architectures: Combining CNNs and LSTMs for complex signal processing
• Practical session: Building an LSTM model to predict high-frequency energy grid load

Module 9: Validation and Evaluation Metrics for Time Series

• Why standard K-Fold Cross-Validation fails for time series data
• Implementing Time Series Split (Forward Chaining) for rigorous validation
• Key metrics: Mean Absolute Error (MAE), RMSE, and sMAPE
• Understanding Mean Absolute Scaled Error (MASE) for model benchmarking
• Analyzing residual plots to check for remaining patterns and model bias
• Practical session: Building a robust backtesting framework to evaluate model performance over time

Module 10: Productionizing Forecasting Pipelines

• Automating the model retraining lifecycle: When to trigger a re-fit
• Strategies for multi-model ensembles and weighted average forecasting
• Monitoring forecast "drift" and accuracy degradation in production
• Building a simple dashboard to visualize forecasts and prediction intervals
• Deployment considerations: Batch forecasting vs. Real-time API endpoints
• Practical session: Creating an end-to-end automated forecasting pipeline using Python and Flask

Requirements:

• Participants should be reasonably proficient in English.
• Applicants must live up to Armstrong Global Institute admission criteria.

Terms and Conditions

1. Discounts: Organizations sponsoring Four Participants will have the 5th attend Free

2. What is catered for by the Course Fees: Fees cater for all requirements for the training – Learning materials, Lunches, Teas, Snacks and Certification. All participants will additionally cater for their travel and accommodation expenses, visa application, insurance, and other personal expenses.

3. Certificate Awarded: Participants are awarded Certificates of Participation at the end of the training.

4. The program content shown here is for guidance purposes only. Our continuous course improvement process may lead to changes in topics and course structure.

5. Approval of Course: Our Programs are NITA Approved. Participating organizations can therefore claim reimbursement on fees paid in accordance with NITA Rules.

Booking for Training

Simply send an email to the Training Officer on training@armstrongglobalinstitute.com and we will send you a registration form. We advise you to book early to avoid missing a seat to this training.

Or call us on +254720272325 / +254725012095 / +254724452588

Payment Options

We provide 3 payment options, choose one for your convenience, and kindly make payments at least 5 days before the Training start date to reserve your seat:

1. Groups of 5 People and Above – Cheque Payments to: Armstrong Global Training & Development Center Limited should be paid in advance, 5 days to the training.

2. Invoice: We can send a bill directly to you or your company.

3. Deposit directly into Bank Account (Account details provided upon request)

Cancellation Policy

1. Payment for all courses includes a registration fee, which is non-refundable, and equals 15% of the total sum of the course fee.

2. Participants may cancel attendance 14 days or more prior to the training commencement date.

3. No refunds will be made 14 days or less before the training commencement date. However, participants who are unable to attend may opt to attend a similar training course at a later date or send a substitute participant provided the participation criteria have been met.

Tailor Made Courses

This training course can also be customized for your institution upon request for a minimum of 5 participants. You can have it conducted at our Training Centre or at a convenient location. For further inquiries, please contact us on Tel: +254720272325 / +254725012095 / +254724452588 or Email training@armstrongglobalinstitute.com

Accommodation and Airport Transfer

Accommodation and Airport Transfer is arranged upon request and at extra cost. For reservations contact the Training Officer on Email: training@armstrongglobalinstitute.com or on Tel: +254720272325 / +254725012095 / +254724452588