Attrasoft

5. Predicting the Stock Market 

5.1 Data Collection From the Internet 
5.2 Data Preprocessing 

5.2.1 Sorting 
5.2.2 Moving Average 

5.3 Commands 
5.4 Prediction with Preprocessing: Intel 4 
5.5 Prediction Without Much Data 
 

 For the sake of discussion, we will predict Intel stock one-month ahead. You can obviously substitute Intel for any other stock or market index. To predict Intel one month ahead, the monthly data is required. You can change the prediction to one-day, one-week, or one-year ahead by substituting daily, weekly, or yearly data, respectively.

 Attrasoft PredictorPro predicts events based on the past history:

• If the past and the future are the same, the prediction is expected to be accurate. 
• If the past and the future are different, the prediction should be used as a reference. 

5.1 Data Collection From the Internet

It is important to avoid any typing in data collection. There are many sites on the Internet, which offer free data. In the following, we will show you how to download data from the �Microsoft Investor� section of the Microsoft Networks. 

Microsoft Excel is required for the following. Assume we want to collect Intel Corp. (Intc) data, here is the procedure:

First Time User:
 

1. Go to: http://investor.msn.com/quotes/quotes.asp?beenthere=1&Page=Research&Item=QuoteDetail and enter "intc";
2. On the page, click "Charts"; 
3. Click "Start Download"; and when prompted to install a Microsoft software, click "yes';
4. You should see a test chart now, and click "I see the chart";
5. Click "Period/10 Years" or other selections you want;
6. To download, click "File/Export Data", at this point, your Excel will be opened and the Intel data is right there. Save the data and the job will be done.

1. Go to http://investor.msn.com/charts/charting.asp?Symbol=intc, on the page enter "intc";
2. Click "Period/10 Years" or other selections you want;
3. To download, click "File/Export Data". At this point, your Excel will be opened and the Intel data is right there. Save the data and the job will be done.

Now, you have obtained the Intel stock data for the last 7 years, and it looks like this: 

Intel Corporation (INTC) 
Monthly prices (Dec 1991 to Nov 1998) 
DATE      HIGH         LOW      CLOSE      VOLUME
Oct-98      90.813      75.813      89.188      393720800
Sep-98      89             69.75        85.75        369103300
Aug-98      92.625      70.938      71.188      440267900
Jul-98        88.25        72.25        84.438      396391200
Jun-98       77.625      65.656      74.125      360081300
�
Apr-92      7.406        6.125        6.688        443011200
Mar-92      8.438       6.438        6.906        424595200
Feb-92      8.594        7.375        7.938        340300800
Jan-92       7.875        5.906        7.484        589994400
Dec-91      6.156        5.031        6.125        260759200

 Now we want:

• Sorting
• Calculating moving averages
• Preparing the PredictorPro Data. 

5.2 Data Preprocessing

5.2.1 Sorting

 Now without typing a single number, you have obtained the Intel data in the Excel spread sheet. Before you can use the data, you have to preprocess it for two or three steps:

• Sorting
• Calculating Moving averages (Optional)
• Prepare PredictorPro data

• Highlight the data;
• click "Data\Sort"; and 
• click "OK". 

Now the data is sorted in the correct order for the PredictorPro. 

5.2.2 Moving Average

To save space, please refer to the last chapter.

5.3 Commands

Stocks like Intel or Microsoft grow exponentially, therefore, you should use the following commands:
 

• Real/+ Exponential
• Real/-- Exponential

5.4 Prediction with Preprocessing: Intel 4

The data set of this example is: 

• 5-month moving average of Intel
• 5-month moving average of SP 500
• 5-month moving average of Microsoft

Clicking "Example/Intel 4 ..." can generate this example.

The goal is predict the 5-month moving average of Intel on Oct-98, which is  80.9378.

 Click "Real/-- Exponential", we get 

Possibility                           Confidence*Probability 
76.0928  1086.51  107.244       92
79.5299  1101.96  103.787       58
---------------------------------------------------
Weighted Average
77.4218  1092.48  105.907 
Highest Probability
76.0928  1086.51  107.244  92
Error of each number
0.859271  3.86403  0.86441

The confidence is too low. To change the Trend from 5 to 4, click "Data/link" and enter 4 under Trend. Click "Real/-- Exponential" again, we get the distribution:
 

Possibility                         Confidence*Probability 
86.404  1078.78  102.058        262
77.8113  1071.05  105.515       4000
76.0928  1086.51  100.329       364
81.2484  1063.32  105.515       330
82.9669  1063.32  105.515       398
82.9669  1071.05  105.515       670
79.5299  1094.23  110.702       160
76.0928  1086.51  107.244       228
81.2484  1101.96  108.973       160
79.5299  1101.96  103.787       126
77.8113  1086.51  107.244       364
76.0928  1094.23  110.702       330
---------------------------------------------------
Weighted Average
78.9408  1075.29  105.665 
Highest Probability
77.8113  1071.05  105.515  4000
Error of each number
0.859271  3.86403  0.86441 

Prediction confidence varies from month to month. The confidence for another month might be much higher. The prediction is 78.9408  ± 0.859271, which is close to 80.9378.

5.5 Prediction Without Much Data

There are times you want to predict a new stock, "A", where no data is available. You can substitute the stock, "A", with another similar stock, "B". 

You have to be careful here: if you use a 5-trend prediction, you must have at least 4 rows of "A" stock. if you use a 6-trend prediction, you must have at least 5 rows of "A" stock.

To predict Intel, the data set of this example is: 

• 5-month moving average of Microsoft
• 5-month moving average of SP 500

Clicking "Example/Intel 5 ..." will generate this example.

The goal is to predict the 5-month moving average of Intel on Oct-98, which is  80.9378.

 Click "Real/-- Exponential", we get 
 

Possibility      Confidence*Probability 
79.0219       34576
76.242         7936
81.8018       20184
84.5816       380
87.3615       256
62.3426       64
---------------------------------------------------
Weighted Average
79.6091 
Highest Probability
79.0219  34576
Error of each number
1.38994

Prediction confidence varies from month to month. The confidence for another month might be much higher. The prediction is 79.6091  ± 1.38994, which hits 80.9378.
 
 

Mail Order: 499.99 (S&H included)

PredictorPro
Attrasoft, Attn.: Gina
P. O. Box 13051
Savannah, GA. 31406, USA

webmaster@attrasoft.com

Copyright © 2001 Attrasoft, Inc. All rights reserved.