3.1 Step 1: Input File Format

3.3 Step 3: Run

3.5 Output File/ Rated Prediction File

User's Guide

Chapter 2 is the quick version of the manual, which listed the minimum requirement. After chapter 2, you should be able to operate the software. However, a few details were left out in chapter 2, like, what is the Precision level, what is Trend; what are all possible commands.

Chapter 3 and 4 will present a detailed user's guide. There will be some repetition between chapter 2 and chapter 3.

The operation has two phases:

• Your Raw Data -- 90% of the work
• Set up a data set (a set of variables)
• Collect data
• Preprocessing if necessary

• Using the Predictor -- 10% of the work
• Prepare input file
• Link this input file to the Predictor
• Run

In this chapter, we will discuss Phase 2: how to use the Predictor. Phase 2 has 3 steps:
 

1. From your raw data, prepare the input file according to the Attrasoft format.

 
2. Link the input file to the Predictor by clicking "Data/Link" (first of 2 clicks).

 
3. Once the file is in the Predictor, click a command to get results (second of 2 clicks).

Predictor presents you with all possible predictions and how valuable the Predictor thinks each prediction is via a confidence number. This number is similar to the number in an Internet Search Engine: the higher that number, the more confidence the Predictor has in that prediction.

Step 1: Input File Format

The best way to learn the input file format is to look at the examples in the Predictor, for example, click "Example/Intel 2". The format is very easy to learn.

The input file must be prepared in the text file format. The Predictor has its own text editor. Or if you wish, you can use any word processor, like Microsoft Word, or WordPerfect; just make sure you save the data file in the text format.

The input file has three sections:

• Comment section
• Number of variables section
• Data section.

Comment Section --- Part 1 of the Input File

The comment section starts with a "*" and ends with another "*". The purpose of this section is to document your data:

• Give a description of the data;
• Specify the data set used;
• Specify the beginning and the ending dates of the data
• . . .

Example:

Number of variables --- Part 2 of the Input File
 

This section has a single integer, which will tell the Predictor how many variables you will use.

Example:

Data Section --- Part 3 of the Input File

This section contains the data.

Example Considering the Intel example which we showed you earlier. You can see a complete example of prepared data, which can used by the Predictor.

This example can be generated by clicking "Example/Intel 2". Note that it has three sections: comment, the number of variables, and the data:
 

*

Purpose: To predict next month Intel.

Data set: 5-month moving average of Intel, Nov-91 through Sep-98

Next 5-month moving average:

10/98 80.9378

*

1

6.7156

7.0282

7.0532

6.9814

6.8876

...

80.2004

78.8254

77.7754

76.4004

77.3878

Step 2: Link Input File To Predictor

Assume we want to link "D_int2a.txt" to the Predictor. There are 4 methods to link the input file:
 
 

Method 1:

• Save the file, "D_int2a.txt", to

• Click command "Data\link" (Figure 3, 4), then enter the "D_int2a.txt" to the first textbox.

• Save the file, "D_int2a.txt", anywhere, say C:\abc\def\D_int2a.txt. Click command "File/Open" to open the file;
• Click command "Data\link" (Figure 3, 4), then enter the "D_int2a.txt" to the first textbox.

Method 3:

• Save your data to:

• Click "Example/a.txt" to link.

• Save your data to file, "a.txt", and leave it anywhere, say C:\abc\def\a.txt. Click command "File/Open" to open the file;

• Click "Example/a.txt" to link.

Input file: example2a.txt

Output file: example2b.txt

These files are automatically connected to the software. When you prepare your own data files, unless you use the default file names above, the data is not connected to Predictor.

Step 3: Run

All you have to do in this step is click one command. There are many commands in the Predictor. If you know the first 6 commands, you will know the rest.

Once you click a command, the results will be in an output file, which is opened for you automatically. We will explain the format of the output file later.

There are six basic commands (See Figure 5). All other commands are derived from these 6 commands. These 6 basic commands are:

Real

+ Linear

-- Linear

0 Linear

+ Exponential

-- Exponential

0 Exponential

These commands are divided into two groups:
 
 

• Linear
• Exponential

• Data is in fixed intervals [a, b];
• Data grows linearly, 1, 2, 3, 4, … .

• Data grows exponentially, 1, 2, 4, 8, … .

+

--

0.

Linear or Exponential
 
 

Example Linear Mode: Data is in fixed intervals.

Let a sequence be { 2, 4, 6, 8, 10, . . . , 98, 100, . . . }.

Example Exponential Mode: Data grows exponentially.

Intel stock is a typical example of the exponential mode:

Upper Bound and Lower Bound

The following two commands produce the upper bound:
 

Real /+ Linear

Real /+ Exponential

The following two commands produce the lower bound:
 

Real /-- Linear

Real /-- Exponential

Commands Lists

In this section, we will introduce the rest of commands.

Real
 

+ Linear basic command

-- Linear basic command

0 Linear basic command

+ Exponential basic command

-- Exponential basic command

0 Exponential basic command

Figure 7. The "Integer" Commands
 
 
 
 

Integer
 

+ Linear

Figure 8. The "Avg/Max" Commands
 
 
 
 

Avg/Max
 

+ Real Linear

Figure 9. The "3-Average" Commands
 
 
 
 

3-Average and 10-Average
 
 
 

+ Real Linear

Output File/ Rated Prediction File

The default output file name is example2b.txt. You can change the output file name by clicking: "Data/Link", or its button on the toolbar, then type in your new data file name.

The "Real" and the "Integer" commands will have the following output format:

• a distribution, which is a list of possibilities and their probabilities
• the weighted average and most probable outcome
• errors

• the weighted average and most probable outcome
• errors

Example Intel 2.
 

1. Click "Example/Intel 2" to link the data to the Predictor. The input file will be opened at this point.

2. Click "Real/-- Exponential" and the output below will be displayed:
 

=================== Beginning =====================

Possibility Confidence*Probability

81.2484 6400

77.8113 10344

76.0928 4235

84.6855 273

88.1226 1

86.404 33

79.5299 168

74.3742 8320

82.9669 261

---------------------------------------------------

Weighted Average

77.476

Highest Probability

77.8113 10344

Error of each number

0.859271

=================== End ==========================
 

Relative Probability or Rating

Relative probability or rating is the ranking the predicted numbers. This number is similar to an Internet Search Engine ranking number.
 

Distribution
 

Predictor presents you with rated possibilities: all possibilities and how valuable the Predictor thinks each one is via a relative probability. These ratings are relative probabilities. In the above example, the distribution is:

Possibility Confidence*Probability

81.2484 6400

77.8113 10344

76.0928 4235

84.6855 273

88.1226 1

86.404 33

79.5299 168

74.3742 8320

82.9669 261

---------------------------------------------------

First of all, the predicted possibilities are

Relative probabilities are proportional to probabilities. For example, let the relative probabilities be (3 5), then they represent the probabilities (3/(3+5), 5/(3+5) ) = (37.5%, 62,5%).

The highest relative probability is called the Confidence Number. This number is given after the weighted-average(s). This number is similar to the number in an Internet Search Engine: the higher that number, the more confidence the Predictor has in that prediction. For each prediction, one Confidence Number is produced. In the above example, the confidence is 10334.

Unfortunately, no quantitative description can be made for the Confidence Number. You can get a feel for this Confidence Number from experience. However, it is vitally important for you to grasp this number. You should ignore the prediction results all together if the confidence number is low.

Error

Of course, you want the error as low as possible. This is not always possible. The error is controlled by a user-defined variable, called Precision level. The higher Precision level is, the lower the error will be. We will discuss the Precision level in the next chapter.