A forecasting model based on a system of artificial neural networks (ANN) is used to predict the direction of the 30-Year U.S. Treasury Bond on a weekly basis. At the close of Friday's market, the 23-variable database is updated with the latest information and the data pre-processed for input to the prediction system. Thirty-two feed-forward neural networks are trained on the new data and then individually recalled to predict the following Friday's market direction. These results are then used as input to a decision model that ultimately determines the final prediction. Forecasting began in 1989, with live trades commencing in 1990. The average accuracy of the buy prediction was 67% over a five-year period, with an average annualized return on investment (ROI) of 17.3%. This compares with an ROI of 13.9% for the Lehman Brothers T-Bond Index. This paper describes the methods used for data selection, training and testing, the basic system architecture, and how the decision model improved...

Abstract not found

form or by any means, without permission in writing from the author. 1 Acknowledgements To my brother Björn who was the best role model a little brother possibly could have had. To my mother Bera who made me see all the possibilities in life. I would like to thank; my wife Jennie for pushing me to get the work done and my children Scott and Naomi for making my life so enjoyable. Tomas for helping me with the lectures and for being such a good friend. Of course my tutor Professor Bo Ekehammar for constructive feedback in spite of lack of time. Agneta Bohlers for proof reading and checking up on my English. Last, but not least, thanks to Jan Bylov, Nordea Markets, Copenhagen and Johnny Thorsell, BörsInsikt AB, Stockholm for raising the money needed for the study. 2 Position-sizing Effects on Trader Performance: An experimental analysis 1 Non-academic literature on stock and futures trading emphasizes the importance of “money management”, here defined as "how much of available capital is to be allocated in a specific market position", also called position size. The effect of position size was experimentally studied by letting two groups trade fictitious capital through a series of trades, with only one variable available for manipulation by the participants, that is, how much of available capital to be put at risk in each and every trade. The treatment group had received a three-hour lecture in position sizing, risk management, and psychological biases, whereas the control group did not. The results showed that participants in the treatment group lost all their money to a lesser extent (p <.01) than those in the control group. However, the treatment group did not gain significantly higher profits than the control group. Traders being able to gain money over the long run were taking smaller positions than losing and bankrupt traders were (p <.0001). By receiving a theoretical education, without any practical training, the risk for a trader of going bankrupt when trading simulated stocks was decreased to a tenth.

Abstract not found

Web-based financial commentary, in which experts routinely express market-related thought processes, is proposed as a means for college students to learn vicariously about financial markets. Undergraduate business school students from a regional university were exposed to expert market commentary from a single financial Web site for a 6week period. When compared to a control group, students in the experimental group were found to possess higher levels of financial market awareness. Degree of engagement, as approximated by measures of project exposure time and effort, was significantly related to market awareness. Finance majors were found to be more engaged in the process than nonfinance majors. Although this study should be considered exploratory in nature, findings support the notion of using Web-based vicarious learning processes in financial education. Future research can extend the generalizability of these findings, as well as shape vicarious learning mechanisms for use across business disciplines.