Forecasting Tourism (2010 Competition, Part I)
Tourism is one of the most rapidly growing global industries and tourism forecasting is becoming an increasingly important activity in planning and managing the industry (from kaggle.com).
The 2010 tourism forecasting competition had two parts. In part I, competitors were tasked with producing forecasts for the next four years, given 518 series of annual tourism data.
The data consist of 518 annual series, each related to some (undisclosed) tourism activity. Tourism activities include inbound tourism numbers to one country from another country, visitor nights in a particular country, tourism expenditure, etc. The series differ in length, ranging from 7-year series to 43-year series. They also differ in the order of magnitude of values. The data are available at www.kaggle.com/c/tourism1/Data (download the file “tourism_data.csv”)
his case will give you experience with forecasting a large number of series. While the competition goal was to achieve the highest predictive accuracy, the goal of this case is to highlight different aspects of the forecasting process that pertain to forecasting a large number of series. For example, easy-to-use visualization tools have a significant advantage for visualizing a large number of series. Note that the multiple series in this case are not likely to be forecasted together. However, it is common to forecast the demand for a large number of series, such as products in a supermarket chain. Another aspect of this case is the use of different predictive measures, and handling practical issues such as zero counts and summarizing forecast accuracy across series.
The assignment provides guidelines for walking you through the forecasting process. Remember that the purpose is not winning the (already completed) contest, but rather learning how to approach forecasting of a large number of series.
1. Plot all the series (an advanced data visualization tool is recommended) – what type of components are visible? Are the series similar or different? Check for problems such as missing values and possible errors.
2. Partition the series into training and validation, so that the last 4 years are in the validation period for each series. What is the logic of such a partitioning? What is the disadvantage?
3. Generate naive forecasts for all series for the validation period. For each series, create forecasts with horizons of 1,2,3, and 4 years ahead ( , and ).
4. Among the measures MAE, Average error, MAPE and RMSE, which are suitable if we plan to combine the results for the 518 series?
5. For each series, compute MAPE of the naive forecasts once for the training period and once for the validation period.
6. The performance measure used in the competition is Mean Absolute Scaled Error (MASE). Explain the advantage of MASE and compute the training and validation MASE for the naive forecasts.
7. Create a scatterplot of the MAPE pairs, with the training MAPE on the x-axis and the validation MAPE on the y-axis. Create a similar scatter plot for validation MASE vs. MAPE. Now examine both plots. What do we learn? How does performance differ between the training and validation periods? How does performance range across series?
8. The competition winner, Lee Baker, used an ensemble of three methods:
∎ Naive forecasts multiplied by a constant trend (global/local trend: “globally tourism has grown “at a rate of 6% annually.”)
∎ Linear regression
∎ Exponentially-weighted linear regression
(a) Write the exact formula used for generating the first method, in the form
(b) What is the rational behind multiplying the naive forecasts by a constant?
(c) What should be the dependent variable and the predictors in a linear regression model for these data? Explain.
(d) Fit the linear regression model to the first five series and compute forecast errors for the validation period.
(e) Before choosing a linear regression, the winner described the following process “I examined fitting a polynomial line to the data and using the line to predict future values. I tried using first through fifth order polynomials to find that the lowest MASE was obtained using a first order polynomial (simple regression line). This best fit line was used to predict future values. I also kept the [R2 ] value of the fit for use in blending the results of the predictor.”
What are two flaws in this approach?
(f) If we were to consider exponential smoothing, what particular type(s) of exponential smoothing are reasonable candidates?
(g) The winner concludes with possible improvements, one being “an investigation into how to come up with a blending [=ensemble] method that doesn't use as much manual tweaking would also be of benefit.” Can you suggest methods or an approach that would lead to easier automation of the ensemble step?
(h) The competition focused on minimzing the average MAPE of the next four values across all 518 series. How does this goal differ from goals encountered in practice when considering tourism demand? Which steps in the forecasting process would likely be different in a real-life tourism forecasting scenario?
At 111papers.com, we value all our customers, and for that, always strive to ensure that we deliver the best top-quality content that we can. All the processes, from writing, formatting, editing, and submission is 100% original and detail-oriented. With us, you are, therefore, always guaranteed quality work by certified and experienced writing professionals. We take pride in the university homework help services that we provide our customers.
As the best homework help service in the world, 111 Papers ensures that all customers are completely satisfied with the finished product before disbursing payment. You are not obligated to pay for the final product if you aren’t 100% satisfied with the paper. We also provide a money-back guarantee if you don’t feel that your paper was written to your satisfaction. This guarantee is totally transparent and follows all the terms and conditions set by the company.Read more
All products that we deliver are guaranteed to be 100% original. We check for unoriginality on all orders delivered by our writers using the most advanced anti-plagiarism programs in the market. We, therefore, guarantee that all products that we submit to you are 100% original. We have a zero-tolerance policy for copied content. Thanks to our strict no plagiarized work rule, you can submit your homework to your professor without worrying.Read more
TThis is one of the most cherished courtesy services that we provide to help ensure that our customers are completely satisfied with our finished products. Delivering the best final product to our customers takes multiple inputs. 111papers.com prides itself on delivering the best university homework help services in the writing industry. And, in part, our free revision policy is how we do it. What’s more, all our revisions are 100% free without any strings attached.Read more
Client privacy is important to use. We know and understand just how important customers value their privacy and always want to safeguard their personal information. Thus, all the information that you share with us will always remain in safe custody. We will never disclose your personal information to any third party or sell your details to anyone. 111 Papers uses the most sophisticated, top-of-the-line security programs to ensure that our customers’ information is safe and secured.Read more
Placing your order with us means that you agree with the homework help service we provide. We, in turn, will endear to ensure that we do everything we can to deliver the most comprehensive finished product as per your requirements. We will also count on your cooperation to help us deliver on this mandate. Yes, we also need you to ensure that you have the highest-quality paper.Read more