different than classical statistical inference using the scientific method. Building adequate prediction models does not necessarily mean that an adequate cause-and-effect model was built, again, due to the multi-collinearity problem.
When considering time series data, a similar framework can be understood. The scientific method in time series problems is driven by the economics or physics of the problem. Various structural forms can be hypothesized. Often there is a small and limited set of Xs that are then used to build multivariate in X times series forecasting models or small sets of linear models that are solved as a set of simultaneous equations. Data mining for forecasting is a similar process to the transaction data mining process. That is, given a set of Ys and Xs in a time series database, the goal is to find out what Xs do the best job of forecasting the Ys. In an industrial setting, unlike traditional data mining, a data set is not normally available for doing this data mining for forecasting exercise. There are particular approaches that in some sense follow the scientific method discussed earlier. The main difference here will be that time series data cannot be laid out in a “designed experiment” fashion. This book goes into much detail about the process, methods, and technology for building these multivariate in X time series models while taking care to find the drivers of the problem at hand.
With regard to process (previously discussed), various authors have reported on the process for data mining transactional data. A paper by Azevedo and Santos (2008) compared the KDD process, SAS Institute's SEMMA (Sample, Explore, Modify, Model, Assess) process and the CRISP data mining process. Rey and Kalos (2005) review the Data Mining and Modeling process used at The Dow Chemical Company. A common theme in all of these processes is that there are many Xs, and therefore some methodology is necessary to reduce the number of Xs provided as input to the particular modeling method of choice. This reduction is often referred to as variable or feature selection. Many researchers have studied and proposed numerous approaches for variable selection on transaction data (Koller 1996, Guyon 2003). One of the main concentrations of this book will be on an evolving area of research in variable selection for time series type data.
At a high level, the data mining process for forecasting starts with understanding the strategic objectives of the business leadership sponsoring the project. This is often secured via a written charter that documents key objectives, scope, ownership, decisions, value, deliverables, timing and costs. Understanding the system under study with the aid of the business subject matter experts provides the proper environment for focusing on and solving the right problem. Determining from here what data helps describe the system previously defined can take some time. In the end, it has been shown that the most time-consuming step in any data mining prediction or forecasting problem is the data processing step where data is defined, extracted, cleaned, harmonized and prepared for modeling. In the case of time series data, there is often a need to harmonize the data to the same time frequency as the forecasting problem at hand. Then there is often a need to treat missing data properly. This may be in the form of forecasting forward, backcasting or simply filling in missing data points with various algorithms. Often the time series database has hundreds if not thousands of hypothesized Xs in it. So, just as in data mining for transactional data, a specific feature or variable selection step is needed. This book will cover the traditional transactional feature selection approaches, adapted to time series data, as well as introduce various new time series specific variable reduction and variable selection approaches. Next, various forms of time series models are developed; but, just as in the data mining case for transaction data, there are some specific methods used to guard against overfitting, which helps provide a robust final model. One such method is dividing the data into three parts: model, hold out, and out of sample. This is analogous to training, validating, and testing data sets in the transaction data mining space. Various statistical measures are then used to choose the final model. Once the model is chosen, it is deployed using various technologies.
This discussion shows how and why it is important that the subject matter experts' knowledge of a company's market dynamics is captured in a form that institutionalizes this knowledge. This institutionalization actually surfaces through the use of mathematics, specifically statistics, machine learning and econometrics. When done, the ensuing equations become intellectual property (IP) that can be leveraged across the company. This is true even if the data sources are in fact public, since how the data is used to capture the IP in the form of mathematical models is in fact proprietary.
The core content of the book is designed to help the reader understand in detail the process described in the previous paragraphs. This will be done in the context of various SAS technologies, including SAS® Enterprise Guide®, SAS Forecast Server and various SAS/ETS® time series procedures like PROC EXPAND, PROC TIMESERIES, PROC ARIMA, PROC SIMILARITY, PROC Xll/12, as well as the SAS® Enterprise Miner™ time series data mining nodes, and others.
1.8 Advantages of Integrating Data Mining and Forecasting
The reason for integrating data mining and forecasting is simply to provide the highest-quality forecasts possible. Business leaders now have a unique advantage in that they have easy access to thousands of Xs, and the knowledge about a process and technology that enables data mining on time series data. With the tools now available through various SAS technologies, the business leader can create the best explanatory (cause and effect) forecasting model possible, and this can be accomplished in an expedient and cost efficient manner.
Now that models of this type are easier to build, they then can be used in other applications, including scenario analysis, optimization problems, and simulation problems (linear systems of equations as well as non-linear system dynamics). All in all, the business decision maker is now prepared to make better decisions with these advanced analytics forecasting processes, methods and technologies.
1.9 Remaining Chapters
The next chapter defines and discusses in detail the process of data mining for forecasting. In Chapter 3, details are given about how to set up an infrastructure for data mining for forecasting. Chapter 4 covers issues with data dining for forecasting applications. This then leads to data collection in Chapter 5 and data preparation in Chapter 6, which has an entire chapter dedicated to the topic since 60–80% of the work lies in this step. Chapter 7 discusses the foundation for the actually doing data mining by providing a practitioner's guide to data mining methods for forecasting. Chapters 8 through 11 present a practitioner's guide to time series forecasting methods. Chapter 12 finishes the book by walking through an example of data mining for forecasting from start to finish.
Chapter 2: Data Mining for Forecasting Work Process
2.3 Work Process with SAS Tools