Course Information
Price
HKD 30,000
CEF Reimbursable
CEF Reimbursable
Study Mode
Location
-
Course Overview
Assessment Methods / 評核方式
(A) Assessment Items and Their Weightings: (1) Continuous Assessment: 50% (Test 25%, Project 25%) (2) Examination: 50% (B) Completion Requirements: (1) The passing grade of the module is C (Grade C is equal to 50% of the overall mark) (C) CEF Reimbursement Requirements: (1) Overall passing grade: Grade C (equals to 50% of the overall mark) (2) 70% of attendance
Entry Requirement / 入學要求
hold a recognized Bachelor's degree in any disciplines with the curricula covering discrete mathematics.
Instructor's Qualifications / 導師資歷
PhD + 4 years of teaching experience
QR Number / 資歷名冊登記號碼
20/000461/L6
QF Level / 資歷架構級別
6
CEF Registration Invalid From / 基金課程登記失效日期
23-DEC-28
(A) Assessment Items and Their Weightings: (1) Continuous Assessment: 50% (Test 25%, Project 25%) (2) Examination: 50% (B) Completion Requirements: (1) The passing grade of the module is C (Grade C is equal to 50% of the overall mark) (C) CEF Reimbursement Requirements: (1) Overall passing grade: Grade C (equals to 50% of the overall mark) (2) 70% of attendance
Entry Requirement / 入學要求
hold a recognized Bachelor's degree in any disciplines with the curricula covering discrete mathematics.
Instructor's Qualifications / 導師資歷
PhD + 4 years of teaching experience
QR Number / 資歷名冊登記號碼
20/000461/L6
QF Level / 資歷架構級別
6
CEF Registration Invalid From / 基金課程登記失效日期
23-DEC-28
What You’ll Learn
(1) Forecasting Goal; Data Characterization; Evaluating Predictive Accuracy (2 hours) (2) Smoothing-Based Forecasting Methods (4 hours): Moving Average; Detrending and Seasonal Adjustment; Exponential Smoothing (Simple, Double and Seasonal). (3) Fourier Series Forecasting Models (6 hours): Cyclical Movement; Spectral Density Function; Periodogram. (4) Regression-Based Forecasting Methods (6 hours): Capturing Trend and Seasonality with Linear Regression; Forecasting with Autocorrelation; Seemingly Unrelated Regression Equations. (5) Box-Jenkins (ARIMA) Models (16 hours): Autoregressive (AR), Moving Average (MA), ARMA and ARIMA processes; Stationarity and Invertibility, Random Walk; Autocorrelation and Partial Autocorrelation Functions, Identification of Models, Estimation of Parameters, Diagnostic Checking and Model Selection. (6) Predictive Analytics in Practice (5 hours): Communicating Predictive Analytics to stakeholders; Forecasting Implementation Issues; Subjective and Naive Forecasts.
