Introduction 1. Predictive analytics in a broader context 1.1 Data mining and Data analytics 1.2 Business Intelligence and Decision Support Systems 1.3 Predictive analytics subset 1.4 Relationship between forecasting, planning and decision-making 2. Predictive analytics modelling rationale and basic ideas 2.1 Time series based forecasting models 2.2 Forecasting horizon 2.3 Data inspection and preparation 3. The role of error measurement 3.1 Error measurement 3.2 Types of errors 3.3 Other error metrics 4. Understanding basic techniques 4.1 Averaging 4.2 Differencing 4.3 Transformations 4.4 Smoothing 5. Associations between and within the time series 5.1 Correlation 5.2 Autocorrelation 5.3 Interpreting autocorrelations 5.4 Corrections to the autocorrelations standard error 5.5 Partial Autocorrelation 5.6 Using Excel functions to calculate partial autocorrelations 5.7 Standard errors for the partial autocorrelations 5.8 Autocorrelations evaluation methods 6. Long-term models - Fitting underlying trend and regression 6.1 Visualisation 6.2 Time series classification 6.3 Curve classification 6.4 Recognising curves 6.5 Fitting curves and extrapolating 6.6 Simple Regression 6.6.1 Variations around the regression line 6.6.2 Estimating parameters 6.6.3 Using Excel Regression Add-in 6.6.4 Basic confidence interval 6.6.5 Changing confidence interval 6.6.6 The alternative confidence interval calculation 6.7 Inspecting Errors in Regression Analysis 6.7.1 Durbin-Watson test 6.7.2 Homoscedasticity 7. Short-term models 7.1 Simple averaging techniques 7.2 Exponential Smoothing 7.2.1 The Standard Errors 8. Medium-term models 8.1 Double moving averages (DMA) 8.2 Double exponential smoothing (DES) 8.3 Triple exponential smoothing (TES) 8.4 Holt’s Double exponential smoothing method 8.5 Damped trend exponential smoothing methods 9. Seasonal models 9.1. Classical decomposition method 9.2 Seasonal adjustments and exponential smoothing 9.3 Simple seasonal exponential smoothing 9.4 Holt-Winters seasonal method
10. State space models 10.1 Defining a state space model 10.2 Excel implementation of the ETS(A,A,A) models 10.3 Manual state space modelling in Excel 10.4 Model selection and forecasting with ETS models 11. Stochastic models 11.1 Types of models 11.2 Model identification 11.2.1 Example of model identification 11.2.2 Estimating autocorrelations 11.2.3 The question of differencing 11.2.4 Testing for zero mean 11.3 Box Jenkins approach to ARIMA Modelling 11.3.1 Basic AR models 11.3.2 Higher AR models 11.3.3 MA models 11.3.4 Mixed ARMA models 11.3.5 Permissible regions 11.3.6 Parameter redundancy 11.4 Model fitting and forecasting 11.4.1 AR(1) forecasts 11.4.2 MA(1) forecasts 11.4.3 ARIMA(1,1,1) forecasts 11.4.4 Forecasting and fitting example 11.5 Model building 11.6 Diagnostic checking 11.7 Seasonal ARIMA models 11.8 Applying the Box-Jenkins method using NumXL Excel add-in 12. Forecasting process 12.1 Selecting the appropriate method 12.2 Qualifying forecasts 12.3 Residual analysis 12.4 Monitoring forecasts (CUSUM) 12.5 Forecast selection 13. Advanced forecasting topics 13.1 Frequency domain analysis 13.2 State space models and the Kalman filtering 13.3 Artificial Neural Networks 13.4 Fuzzy Logic 13.5 Chaos theories 13.6 Econometric time series analysis 13.7 Forecasting in the supply chain Appendix 1 Understanding Excel basics Referencing cells Functions Charts and graphs Combined charts Excel Add-ins Appendix 2 Understanding elementary statistical concepts Histograms Descriptive statistics Two variables Samples and distributions Confidence interval Bibliography Index
You can view Chapter 5 and Chapter 13.1 as an example to illustrate the style and the complexity of the material.