- Explain how the predictions made using analytics are somewhat different than those from traditional forecasting models. Are the data used different? Are the types of predictions different?
- Suppose that you have been asked to recommend a forecasting technique that would be appropriate to prepare a forecast, given the following situational characteristics:a. You have 10 years of
- What are the two main things to consider when selecting a forecast method? Why?
- Describe the nine-step forecast process presented in the chapter.
- What two groups must communicate well in order for the forecast process to be effective? Explain why.
- Explain the process of going from raw data to actions based on a forecast.
- Discuss how forecasting has moved from purely judgmental methods to highly complex methods.
- Why mine text at all? Isn’t language so complex that little useful insight can be gained through machine learning methods?
- In previous chapters, we used data mining diagnostic statistics such as confusion matrices and lift charts to evaluate models. Are these types of statistics useful in text mining?
- In the chapter, the two different text mining approaches were both used to mine text: “bag of words” analysis and “natural language processing.” What is the significant difference between the
- What is meant by “natural language processing"?
- What is meant by “bag of words” analysis?
- What is meant by the term dimension reduction?
- What method explained in this chapter is a concept in analytics of approximating the sampling distribution of a statistic by repeatedly sampling from a given sample of size n.
- “Boosting” may only be used with Naïve Bayes algorithms. Is this a true statement?
- “Bagging” is a short form of “bootstrap aggregation.” Explain conceptually how bagging is accomplished in software. Why might bagging increase the predictive capacity of an underlying
- What are “weak learners” and are they used by bagging or boosting? Explain the concept of a weak learner.
- Explain the fundamental difference between “boosting” and “bagging.”
- What is the basic concept underlying an “ensemble” model?
- Explain what is meant by Bayes’ theorem as used in the Naive Bayes model. Lift Chart (Validation Dataset) Decile-wise Lift Chart (Validation Dataset) 10- 250 200- 150 100- 2- 50 of 2000 12 3 4 5678
- Calculate the classification error rate for the following confusion matrix. Comment on the pattern of misclassifications. How much better did this data mining technique do as compared to a naive
- A data mining algorithm has been applied to a transaction dataset and has classified 88 records as fraudulent (30 correctly so) and 952 as nonfraudulent (920 correctly so). Which of the following
- The lift chart and the confusion matrix are both standard diagnostic tools used to evaluate a data mining algorithm. Don’t the two measures show-display the same information? Explain any
- Data has the characteristic of “non-rivalry.” What is non-rivalry and why is it important to realize that data has this characteristic?
- In the Universal Bank data in this chapter only 10% of the records represented customers that had taken out a personal loan (the target variable). If we were to score a new customer based upon the
- Show the computation for the misclassification rate of this confusion matrix.Confusion MatrixActual\Predicted01097020128
- The validation data set confusion matrix for the Universal Bank data classification model is shown.How many records were in the validation data set? How many of the records were correctly classified
- Some data mining algorithms work so “well” that they have a tendency to overfit the training data. What does the term “overfit” mean and what difficulties does overlooking it cause for the
- In the Universal Bank classification model estimated with XLMiner the software produced the validation data set lift chart shown.How is the naïve model displayed in the diagram? What does the other
- How do “structured” and “unstructured” data differ? Which is the more prevalent form of data?
- The first step in data mining procedures according to SAS and IBM/SPSS is to “sample” the data. Sampling here refers to dividing the data available for analysis into at least two parts: a
- A classification model's misclassification rate on the validation set is a better measure of the model's predictive ability on new (unseen) data than its misclassification rate on the training set.
- The data below show retail sales at hardware stores in the United States monthly between January 1992 and December 2005. The data are in millions of dollars and are not seasonally
- The following table contains quarterly data on Upper Midwest car sales (CS) in thousands for 1996 Q1 through 2016 Q4:
- A regional supplier of jet fuel is interested in forecasting its sales. These sales data are shown for the period from 2002Q1 to 2017Q4 (data in billions of gallons):
- The Bechtal Tire Company (BTC) is a supplier of automotive tires for U.S. car companies. BTC has hired you to analyze its sales. For this problem, do all the work in Forecast X™ and be sure to
- Carl Lipke is the marketing VP for a propane gas distributor. He would like to have a forecast of sales on a quarterly basis, and he has asked you to prepare a time-series decomposition model. The
- A tanning parlor located in a major shopping center near a large New England city has the following history of customers over the last four years (data are in hundreds of customers and months are the
- How do true cycles and the cycles typically found in business data differ?
- How is the long-term trend determined for a time-series decomposition model?
- What is the difference between seasonal factors and seasonal indices?
- Discuss the trend, the seasonal, and the cyclical components.
- Explain the similarity between how time-series decomposition and Winters’ exponential smoothing deal with seasonality.
- Your company produces a favorite summertime food product, and you have been placed in charge of forecasting shipments of this product. The historical data below represent your company’s past
- Develop an example to show how to set up a data file to apply regression analysis to combine forecasts.
- Outline the process for combining forecast models explained in this appendix.
- AmeriPlas, Inc., produces 20-ounce plastic drinking cups that are embossed with the names of prominent beers and soft drinks. The sales data
- a. Construct a time-series graph of the sales data for HeathCo’s line of skiwear. Does there appear to be a seasonal pattern in the sales data? Explain why you think the results are as you have
- In Chapter 4, you worked with data on sales for a line of skiwear that is produced by HeathCo Industries. Barbara Lynch, product manager for the skiwear, has the responsibility of providing forecasts
- The following inventory pattern has been observed in the Zahm Corporation over 12
- Explain things that should be considered when selecting independent variables for a multiple regression model that will be used to make a forecast.
- Describe some ways dummy variables can be useful in regression models.
- Explain what is meant by a "dummy variable."
- Describe how a regression plane differs from a regression line.
- Explain the five-step process for evaluating a multiple regression model.
- Explain the difference between bivariate (simple) regression and multiple regression.
- Fifteen mid-western and mountain states have united in an effort to promote and forecast tourism. One aspect of their work has been related to the dollar amount spent per year on domestic travel
- Carolina Wood Products, Inc., a major manufacturer of household furniture, is interested in predicting expenditures on furniture (FURN) for the entire United States. It has the following data by
- Dick Staples, has mentioned to Barbara Lynch that he has found both the unemployment rate and the level of income to be useful predictors.a. Suppose that Ms. Lynch provides you with the following
- Barbara Lynch is the product manager for a line of skiwear produced by HeathCo Industries and privately branded for sale under several different names, including Northern Slopes and Jacque Monri. A
- Mid-Valley Travel Agency (MVTA) has offices in 12 cities. The company believes that its monthly airline bookings are related to the mean income in those cities and has collected the following
- Nelson Industries manufactures a part for a type of aircraft engine that is becoming obsolete. The sales history for the last 10 years is as
- Explain what is meant by heteroscedasticity.
- Explain the difference between the most common kind of correlation (the Pearson product moment correlation, discussed in Chapter 2) and serial correlation.
- Explain the difference between a simple trend model and a causal model.
- In this chapter, you learned four steps that should be used to evaluate a regression model. What is the first step and why is it so important? Explain the other three steps, indicating what you
- How can seasonal data be forecast with a simple bivariate linear regression model? Explain the deseasonalize-forecast-reseasonalize process. How does the material in this chapter suggest that
- Why is it useful to look at data in a graph as well as in a table? What is the main advantage of seeing a graph of the data?For most people looking a long tables of numbers provides little useful
- What is an "event model?" Give some examples of when such a model might be useful.
- What are some methods that might be useful to forecast "new products" for which there are few historical observations?
- What data pattern would suggest the use of a Winters' exponential smoothing model?
- When is a Holt's exponential smoothing model most appropriate?
- For what type of data pattern would a simple exponential smoothing model be good as a forecast method?
- Why is the term exponential used when describing exponential smoothing forecast models? negative slope
- How are simple moving averages models different from exponential smoothing models?
- Describe what is meant by the term moving average? When would a moving average be an appropriate forecast method?
- Monthly data from March 2014 through September 2017 are provided below for the number of lunches served in public schools. You are charged with making a 12-month forecast of the meals to be served.
- The data in the table below are for retail sales in book stores by quarter.U.S. Retail Book Sales (in Millions of Dollars,
- The data in the table below represent warehouse club and superstore sales in the eastern and central United States on a monthly basis. The data are in millions of dollars.
- Plot the data presented in Exercise 7 to examine the possible existence of trend and seasonality in the data.Prepare three separate exponential smoothing models to forecast the full-service
- The number of service calls received at LaFortune Electric during four months is shown in the following table: Month…………..Number of Service
- The number of tons of brake assemblies received at an auto parts distribution center last month was 670. The forecast tonnage was 720 for last month. The company uses a simple exponential smoothing
- Forecasters at Siegfried Corporation are using simple exponential smoothing to forecast the sales of its major product. They are trying to decide what smoothing constant will give the best results.
- Consider the following data on full-service restaurant sales. Calculate both the three-month and five-month moving averages for these data, and compare the forecasts by calculating the mean absolute
- Consider the following rates offered on certificates of deposit at a large metropolitan bank during a recent year:Use a three-month average to forecast the rate for the following
- Home sales are often considered an important determinant of the future health of the economy. Thus, there is widespread interest in being able to forecast home sales (HS). Quarterly data for HS are
- Use exploratory data analysis to determine whether there is a trend and/or seasonality in mobile home shipments (MHS). The data by quarter are shown in the following
- In a sample of 25 classes, the following numbers of students were observed.ClassNumber of studentsClassNumber of
- Twenty graduate students in business were asked how many credit hours they were taking in the current quarter. Their responses are shown as follows.Student NumberCredit HoursStudent NumberCredit
- As the world’s economy becomes increasingly interdependent, various exchange rates between currencies have become important in making business decisions. For many U.S. businesses, the Japanese
- CoastCo Insurance, Inc., is interested in developing a forecast of larceny thefts in the United States. It has found the following data:YearLarceny Thefts*YearLarceny
- Suppose that you work for a major U.S. retail department store that has outlets nationwide. The store offers credit to customers in various forms, including store credit cards, and over the years has
- Go to the library and look up annual data for population in the United States from 2000 through the most recent year available. This series is available at a number of Internet sites, including
- Suppose that you work for a U.S. senator who is contemplating writing a bill that would put a national sales tax in place. Because the tax would be levied on the sales revenue of retail stores, the
- In the chapter, you learned about many metrics that can be used to evaluate forecast accuracy. The MAPE was one of those that may be the most common in use. Explain what the MAPE tells a forecaster.
- In this chapter, you saw an example of a naive forecast. Why do you think it is given that name? Describe how the naive forecast is developed.
- The process of forecasting new products is difficult. Why? How can new products be forecast?
- Explain how forecasting relates to having an efficient supply chain.
- How does the organization of the material in this book relate to the stages of the evolution of prediction?
- Describe the three phases of the evolution of forecasting/prediction.