G. R. Pugh & Company (Cranford, NJ) has been using a BrainMaker neural network trained on three-to-four years of historical data with an XT-compatible PC to help forecast the next year's corporate bond prices and ratings of 115 public utilities companies. "An XT is more than sufficient; it's a fast program," company president Mr. George Pugh notes. Learning to use the program and create a neural network from scratch took only two days. The network trained itself to predict bond prices in about four hours.
G. R. Pugh & Company does consulting to predict bond prices for the public utility industry. He maintains databases with financial and business information on the companies, advises with business forecasts and credit risk assessments and predicts the financial and operating health of these companies. His expertise is also used by the brokerage industry. He advises clients by forecasting on the selection of good corporate bonds. His clients need to know more accurately which bonds represent good investments for their customers. Both increases and decreases in bond value provide the potential for profitable investment.
Mr. Pugh announced that predicting bond prices with BrainMaker neural network software has been more successful than discriminant analysis and forecasting methods he has used, and even a little better than a person could do. "Discriminant analysis methods are good for getting the direction of lively issues, but neural networks pick up the subtle interactions much better," he explains. The network categorizes the ratings with 100% accuracy within a broad category and 95% accuracy within a subcategory. The mathematical method of discriminant analysis was only 85% accurate within a broad category. (Bonds are rated much like report cards, with broad category ratings such as A, B, C, etc. A subcategory could be A+, for example).
According to Mr. Pugh, "BrainMaker was able to pick up some of the interplays in the inputs that statistical analysis couldn't get." The network makes a significant contribution to his analysis. "The network allows me to pick up things that are not obvious with typical analysis," he says.
Moreover, nearly all of the network's difficulties were found to be associated with companies that were experiencing a particularly unusual problem (such as regulatory risk) or had an atypical business relationship (such as being involved in a large sale and lease-back transaction). Ratings also tend to be subjective; financial items are not the only things considered by the rating companies. These influences were not represented in the training facts and this makes predictions difficult.
The trained network forecasts next year's Standard & Poor's and Moody's corporate bond ratings (both are industry standards) from the previous year's S & P and Moody's ratings and 23 other measures of each company's financial strength, such as income, sales, returns on equity, five-year growth in sales, and measures of investment, construction, and debt load. Each of these factors is assigned its own input neuron, and each company's ratings for next year are the outputs of the network.
A basic neural network similar to Mr. Pugh's:
INPUTS
last year S&P rating
last year Moody rating
financial strength
income
sales
returns on equity
assets
debt load
5-year growth in sales
investments
construction
etc.
OUTPUTS
next year Moody rating
next year S&P rating