Proposing a Method for Forecasting Interrupted Time Series based on Fuzzy Logic: a System Dynamics Approach

Modarres Vahid, Melika | 2022

50 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 55075 (01)
  4. University: Sharif University of Technology
  5. Department: Industrial Engineering
  6. Advisor(s): Khedmati, Majid
  7. Abstract:
  8. Performing analysis and forecasting is crucial. Better forecasting will lead to better decisions. One method for predicting the future is time series analysis. In reality, it is common for an intervention to occur and alter the characteristics of a time series. In recent years, interrupted time series analysis has been receiving a lot of attention. A new forecasting method for interrupted time series has been developed in this study. This is a system dynamics-based approach. At every stage of the approach, system thinking is incorporated. In order to model the effects of a given intervention, common modes of behavior in dynamic systems are used. Furthermore, control theory has been used to demonstrate the mentioned common modes of behavior of dynamic systems by using transfer functions and responses to pulse and step inputs. In a system dynamic approach, the time series is viewed as a whole system that includes the interactions among the elements. Therefore, delays, non-linearities, unexpected effects of an intervention, and policy resistance are factored in, leading to more realistic forecasts. Additionally, for clarification, the proposed approach is used to assess the effects of vaccination on the number of deaths caused by covid-19 in Iran. To reflect the expected effects, a goal-seeking behavior is chosen. The goal-seeking behavior is shown through unit-step response of first-order systems. Since there is no additional information available for the matter at hand, a fuzzy inference system has been constructed to determine the parameters of the response function. Last but not least, the proposed approach appears to provide a more realistic prediction of future observations by reducing the mean percent forecast errors
  9. Keywords:
  10. Time Series ; Fuzzy Logic ; Intervention ; System Approach ; Interrupted Time Series Analysis

 Digital Object List