Chapter 11 of the Practical Time Series Forecasting textbook (pages 211-214).
“Background: Forcasting transportation demand is important for multiple purposes such as staffing, planning and inventory control. The public transport system in Santiago de Chile has gone through a major effect of reconstruction. In this context, a business intelligence competition took place in october 2006, which focused on forecasting demand for public transportation. This case is based on the competition, with some modifications.
Problem Description: A public transportation company is expecting increased demand for its services and is planning to acquire new buses and extend its terminals. These investments require a reliable forecast of future demand. the companys data warehouse has data on each 15 minute interval between 630 and 2200 on the number of passengers arriving at the terminal. as a forecasting consultant you have been asked to create a forecasting method that can generate forecasts for the number of passengers arriving at the terminal.
Available Data: Part of the historic information is available in the file. The gile contains the worksheet “historic information” with known demand for a 3 week period separated into 15 min intervals. the second wowrksheet (“future”) contains data and times for a future 3 day period. For which forecasts should be generated (as part of the 2006 competition)
Assignment Goal: Your goal is to create a model/method that produces accurate forecasts. to evaluate your accuracy partition the given historic data into two periods: atraining period (the first two weeks) and a vallidation period (the last week). Models should be fitted only to the training data and evaluated on the validation data. Although the competition winning criterion was the lowest mean absolute Error (MAE) on the future 3 day data, this is not the goal for the assignment. Instead if we consider a more realistic business context our goal is to create a model that generates resonably good forecasts on any time day of the week. consider not only predictive metrics such as MAE, MAPE, and PMSE, but also look at actual and forecasted values overlaid on a time plot.
Assignment: 1. name of the method/combination of methods. 2. a breif description of the method/combination. 3. all estimated equations associated with constructing forecasts from this method. 4. The MAPE and MAE for the training period and the calidation period. 5. Forecasts for the future period (march 22-24) in 15 min intervals. 6. a single chart showing the fit of the final version of the model to the entire period (including training, validation, and future) note that this model should be fitted using the combined training+validation data
This case is to practice forecasting public transportation demand in Santiago, Chile using the smoothing methods that we have learned thus far.
Read the information on those pages of the textbook.
The data can be found in bicup2006.xls
You response to the case will include two parts:
(1) A memo written to the Chief Operations Officer of Transantiago that describes the model and method and presents the 3-day forecast (March 22, 23 and 24) at 15-minute intervals in as non-technical language as possible.
(2) A technical appendix to your memo that includes: the name of the model/combination of model used a description of the method or combination all estimated equations, etc. associated with constructing the forecasts the MAPE and MAE for the training period and the validation period forecasts for the future period (March 22-24) at 15-minute intervals a graph showing the fit of the final model for the entire period (including training, validation and future), fitted using the combined training and validation data any additional information that would be useful in understanding or recreating your forecast a list of any references consulting in preparing your answer