DOC PREVIEW
UW-Madison ECE 539 - ANN Approach to Revenue or Profit Estimation

This preview shows page 1-2-3-4 out of 11 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 11 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 11 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 11 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 11 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 11 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

ANN Approach to Revenue or Profit EstimationInitial Design ConsiderationsInitial Design Considerations <cont’d>Slide 4Data GatheringNetwork DesignInput ChoiceOutput ChoiceResultsConclusions & New InsightsSlide 11By Charles A. Clark 1ANN Approach to Revenue or Profit EstimationANN Approach to Revenue or Profit EstimationUniversity of Wisconsin-MadisonBy Charles A. Clark 2Initial Design ConsiderationsInitial Design ConsiderationsInitially, I attempted to create a ANN that would predict future stock prices based upon:–Previous Stock Growth Percentages–Financial Statistics of a firmI quickly found that in today’s market, stock prices may have little in common with a firm’s financial outlook and health.Examples:–Ebay,Amazon,Biotech Industry, etc.By Charles A. Clark 3Initial Design Considerations<cont’d>Initial Design Considerations<cont’d>The next move was to narrow the focus of my project to a growth indicator that could be considered a derivative of financial health.–I settled on Revenue growth–Note: This network could easily be changed to support profit growth prediction as well other financial components. The only restriction is the need for enough supporting data.By Charles A. Clark 4Initial Design Considerations<cont’d>Initial Design Considerations<cont’d>The final consideration was upon the data itself. –First, I could only find inexpensive (read FREE) historical financial data for the last three year.–Second, I knew that the training of the network would require data for only one industry at a time. Basically, each industry operates efficiently with slightly different expectations on capital asset liability, expected ratios of short-term to long-term debt, and various other indications. To include a firm from a separate industry would be to train or test that firm unfairly.By Charles A. Clark 5Data GatheringData GatheringI needed to gather standardized and extensive financial data on each firm for this project. For this I ended up using two sources.–http://biz.yahoo.com/research/indgrp/ provided me with stock grouping by industry–http://www.money.net provided me with the information resource of historical financial information. Unfortunately their data only went back 3 years. A more cumulative training would have been interesting.By Charles A. Clark 6Network DesignNetwork DesignI choose to use a MLP for this project because of my familiarity with it as well as it’s flexibility.–Notes on the specific design of the MLP Sigmoid Activation Function 25 inputs for year against year training 50 inputs for comparative training (includes data from both firms) 1 output for all designsBy Charles A. Clark 7Input ChoiceInput ChoiceI choose my input directly from the financial information offered on money.netThe following data was taken from each firm’s Income Statement, Balance Statement, & Cash Flow Statement.• Revenue• Operating Expenses• Operating Income• Income Before Taxes• Income Taxes• Pri/Bas EPS Ex. Xord• Dilutd EPS Ex. Xord• Primary/Basic Av. Share• Total Current Assets• Total Assets• Total Current Liabilities• Total Liabilities • Total Equity• Net Income• Depreciation & Amort.• Total Operating Cash Flow• Total Investing Cash Flow• Total Financing Cash Flow• Net Change in Cash• Receivables• Accounts Payable• Common Dividends/Shr.•Outstanding SharesBy Charles A. Clark 8Output ChoiceOutput ChoiceFor the year vs. year testing and training, each firm’s revenue is compared with that fir’s revenue for the following year. The percentage growth is calculated and if it is higher than a threshold X, in this case 10% we set that firms target output to be 1.In comparative testing, we must take the ratio of one firm’s revenue growth versus another firm’s revenue growth. If firms A (located in the outer loop) has a higher % of growth the target output will be 1, otherwise if firm B has the higher % than the target output will be 0.By Charles A. Clark 9ResultsResultsWhile training with both the 1997 and the 1998 data I was able to obtain an average revenue prediction rate of 61.3% over about a hundred trials. The max of my testing was as high as 70 % and the low was about 52 %. Training with the 1997 data and testing on 1998, my network obtained an average of 63.4% with a range of 70.2% to 54 %. Training with the 1998 data and testing on 1997, the network scored an average of 60.5% with a range of 65% to 52%.By Charles A. Clark 10Conclusions & New InsightsConclusions & New InsightsThe results that I obtained were competitive in the sense that the pointed to the ability of a neural net to pull viable conclusions for the data. While these conclusions are not of the investment caliber, I believe the fault of this resides with the data itself. Adding the element of anticipation or expectation into the data by adding a whisper number or expected increase data column should help to push the data in the right direction.The reason that I did not initially propose this is because retrieving the PAST data on whisper number on a large number of stocks would’ve been nearly impossible. Second whisper data tends to be extremist. Often it overshoots the true growth or decline of a firm. However with the bulk of the data predicting conservatively, a whisper data field might be a good tweak. (as an aside, many of the mis-predictions were clustered around the target boundary line. This points to the validity of the data for not predicting wild results and further suggests a whisper data point might help.By Charles A. Clark 11Conclusions & New InsightsConclusions & New InsightsThe second change that I would like to make to the network is the target space. The real point at which a firm becomes investment grade is when it’s growth is expected at > than 15%. Also there is a fair amount of clumping at 10% growth since that is the industry norm. Splitting the Output space into perhaps three outcomes of –Firm X <5% (sell) –5%< Firm X <15% (hold)–Firm X > 15%


View Full Document

UW-Madison ECE 539 - ANN Approach to Revenue or Profit Estimation

Documents in this Course
Load more
Download ANN Approach to Revenue or Profit Estimation
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view ANN Approach to Revenue or Profit Estimation and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view ANN Approach to Revenue or Profit Estimation 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?