L2 Forecasting methods and techniques.pptx

presentation of forecasting methods and techniques . quantative and qualitative methods time series

1. Nile valley University Faculty of Graduate studies Ph.D. : Total of Technology August 2023

2. Production Management Lec . 2: Forecasting Fundamentals

3. Outline Fundamental Principles of Forecasting Major Categories of Forecasts Forecast Errors Computer Assistance

4. FUNDAMENTAL PRINCIPLES Of FORECASTING Forecasting is a technique for using past experiences to project expectations for the future . Forecasts are almost always wrong . Forecasts are more accurate for groups or families of items . Forecasts are more accurate for shorter time periods . Every forecast should include an estimate of error . Forecasts are no substitute for calculated demand

5. 2.2 MAJOR CATEGORIES Of FORECASTS Qualitative and. Quantitative

6. 2.2 MAJOR CATEGORIES Of FORECASTS Qualitative forecasting are generated from information that does not have a well-defined analytic structure . key characteristics: based on personal judgment Subjective Rapid results. used for individual products

7. Qualitative forecasting methods Market surveys : questionnaires submitted to potential customers in the market . Delphi or panel consensus: panel of experts. Life cycle analogy: similar product. Informed judgment: opinion of sales represntives

8. Quantitative Forecasting-Causal key characteristics: based on relationship between variables, or one measurable variable "causes" the other to change. the causal variable can be measured. often bring excellent forecasting results . Learning from model development. seldom used for product, but commonly used for entire markets. time-consuming and very expensive.

9. Quantitative Forecasting-Causal Methods Input-output models large and complex models, examine the flow of products throughout the entire economy. require a substantial quantity of data, making them expensive and time-consuming to develop . Econometric models . involve a statistical analysis of various sectors of the economy . Simulation models . Expensive and time-consuming. Regression . Causal methods also called extrinsic forecasts

10. Quantitative forecasting-Time Series Methods Based on assumption is that past demand follows some pattern, and that pattern can be analyzed and used to develop projections for future demand. called intrinsic forecasts . Capture random pattern. Trend pattern. seasonal pattern

11. Quantitative forecasting-Time Series Methods

12. Quantitative forecasting-Time Series Methods

13. Quantitative forecasting-Time Series Methods

14. Quantitative forecasting-Time Series Methods Simple moving averages are nothing more than the mathematical average of the last several periods of actual demand. : Where: F is the forecast t is the current time period, meaning F t is the forecast for the current time period A t is the actual demand in period t, and n is the number of periods being used.

15. Points to consider: Forecast line is smoother Forecasts lag behind the actual.

16. Quantitative forecasting-Time Series Methods Weighted moving averages: SMA gives all n data equal weight = 1/n

17. Quantitative forecasting-Time Series Methods Simple exponential smoothing Were α is smoothing factor constant. All historic data included Recent data has greater weight larger the alpha value, the more of the forecast error is added. It makes forecast more responsive to actual changes in demand ,

18. Quantitative forecasting-Time Series Methods

19. Quantitative forecasting-Time Series Methods

20. Quantitative forecasting-Time Series Methods Regression: Where : a is slope off line b the x-intercept for data a = 18.8 b= 268.3 The result next slide

21. Quantitative forecasting-Time Series Methods Seasonal index multiplier found by the ratio of actual to forecasted demand

22. FORECAST ERRORS Mean forecast error : ( bias .) Mean Absolute Deviation (MAD ). Tracking Signal .