Linda Salchenberger

A Neural Network Model for Estimating Option Prices

A neural network model that processes financial input data is developed to estimate the market price of options at closing. The networks ability to estimate closing prices is compared to the Black-Scholes model, the most widely used model for the pricing of options. Comparisons reveal that the mean squared error for the neural network is less than that of the Black-Scholes model in about half of the cases examined. The differences and similarities in the two modeling approaches are discussed. The neural network, which uses the same financial data as the Black-Scholes model, requires no distribution assumptions and learns the relationships between the financial input data and the option price from the historical data. The option-valuation equilibrium model of Black-Scholes determines option prices under the assumptions that prices follow a continuous time path and that the instantaneous volatility is nonstochastic.

Using neural networks to forecast the S&P 100 implied volatility

The implied volatility, calculated using the Black-Scholes model, is currently the most popular method of estimating volatility and is considered by traders to be a significant factor in signalling price movements in the underlying market. Thus, the ability to develop accurate forecasts of future volatility allows a trader to establish the proper strategic position in anticipation of changes in market trends. A neural network has been developed to forecast future volatility, using past volatilities and other options market factors. The performance of this network demonstrates its value as a predictive tool.

Structured development techniques for user-developed systems

Abstract The demand for individual control over information and processing is increasing with the availability of inexpensive hardware, user-friendly software, and greater numbers of sophisticated users. Since it is well-known that structured methods can improve productivity and system quality, they should be adapted to aid in end user computing. In this paper, a set of guidelines for applying a structured methodology to end user developed applications, based on established structured tools and techniques, is presented with an implementation strategy. Two cases in which the methodologies and tools were successfully applied by end users with information systems staff support are discussed.

Beating the best: A neural network challenges the Black-Scholes formula

A neural network model which processes financial input data is presented to estimate the market price of options. The networks ability to estimate option prices is compared to estimates generated by the Black-Scholes model, a traditional financial model. Comparisons reveal that the neural network outperforms the Black-Scholes model in about half of the cases examined. While the two modeling approaches differ fundamentally in their methodology for determining option prices, some common results emerge. While the neural network performs better than Black-Scholes on prices out-of-the-money, estimations near the expiration data are accurate for both.<<ETX>>

Using neural networks to aid the diagnosis of breast implant rupture

Abstract From a database consisting of 78 inplants that were surgically removed, ultrasound findings and surgical results were used to train and test backpropagation and radial basis function (RBF) neural networks using the round-robin or leave-one-out method. Receiver-operating-characteristic (ROC) curve analysis was applied to compare the performance of the different neural networks with that of the radiologists involved in the ultrasound evaluations. The neural networks outperformed the radiologists involved. RBF networks performed better in this classification problem than did backpropagation networks. The best performing network utilized, in addition to the findings, the (unaided) diagnosis of the radiologist. Thus, the ‘team’ approach appears to provide the best results. Also, the network performed particularly well in those cases in which the radiologist classified the implant as indeterminate. The results suggest that a neural network using findings extracted from sonograms by experienced sonographers can be of great assistance to physicians with the diagnosis of implant rupture.

An empirical study of the use of business expert systems

Abstract The evolution of computers from computational tools to “thinking machines” is causing businesses to evaluate their views of the computers role. The inevitable availability of smart computers leads to questions of how and when fifth generation hardware and software will be integrated into corporate culture. Here, we present the results of a survey given to information systems managers to determine the extent of expert systems development by data processing departments and expert systems usage in organizations. The attitudes of management toward the future of expert systems are also discussed using the survey data. It was discovered that, while computer managers are receptive toward this new tool, most have no definite plans to develop expert systems in the near future. These results seem to be in conflict with other evidence about the growing numbers of expert systems in business applications. One explanation is that this new technology is part of the continuing “grass roots” movement of end-user computing.

A small business inventory DSS: design, development, and implementation issues

The availability of decision support and productivity software is providing opportunities for small businesses to develop systems which utilize operations research models to support decision-making. A framework for the development of small business decision support systems is presented and is applied to inventory management decision support system which utilizes economic order quantity models. Issues related to design, development, and implementation of small business decision support systems are discussed in detail and many aspects of the framework are illustrated using the inventory decision support system in a small business environment.

Do-ahead replaces run-time: a neural network forecasts options volatility

Compares three methods of estimating the volatility of daily S&P 100 Index stock market options. The implied volatility, calculated via the Black-Scholes model, is currently the most popular method of estimating volatility and is used by traders in the pricing of options. Historical volatility has been used to predict the implied volatility, but the estimates are poor predictors. A neural network for predicting volatility is shown to be far superior to the historical method.<<ETX>>

Sole owner harvesting policies under the threat of entry: A two-stage linear game

Abstract In this paper, we analyze harvesting policies for a producer who is guaranteed exclusive harvesting rights to a renewable resource for a specified period of time. A second producer may enter the market after these rights have expired and if entry occurs, the duopoly stage is modeled as a noncooperative differential game. We assume that the price and average costs are constant and that the harvest rate is linearly dependent upon the stock level and the effort expended. After the solution to the duopoly game is presented, we give the solution to the two-stage profit maximization problem of the incumbent. A modified most rapid approach path solution is shown to be optimal under certain conditions.

A strategy for integrating artificial intelligence technology into a graduate business curriculum

There is much evidence that artificial intelligence technology is beginning to emerge from the research lab and move into business computer-based systems. Applications of artificial intelligence in business in the areas of finance, manufacturing, and software development and data management, are increasing. Since graduate programs in business attempt to provide students with background in, and experience with computer-based modeling, it is important that universities anticipate and plan for the integration of artificial intelligence technology into the Masters degree in Business Administration (MBA) program. The purpose of this paper is two-fold. First, a framework for integrating artificial intelligence applications and methodology into the curriculum of a graduate business program is presented. Second, an implementation strategy is discussed and detailed examples are given.