NN literature

This paper is an attempt to unravel the relationship between the economic variables and the returns of the mutual funds in Indian context. The paper considers the monthly data of several economic variables like the national output, interest rate, inflation, exchange rate, money supply, aggregate equity market between 1999 and 2004, and tries to reveal the relative influence of these variables on the net asset values of selected mutual fund schemes. Compared to the earlier similar attempts made in the context of developed markets, this paper applies the modern non-linear technique like Artificial Neural Network and tries to predict mutual fund net asset values on the basis of the chosen variables. The finding shows that certain variables like the interest rate, money supply, inflation rate and the equity market have considerable influence in the net asset value movement in the considered period, while the other variables have very negligible impact on the mutual fund returns.

Files:

Neural Network Models for Forecasting Mutual Fund Net Asset Value.pdf 226 kb

whisperer 2016.08.29 15:41 #8

seekers_:

Anybody has this for our trading platform?

John Seekers 2016.09.04 12:33 #9

There can be little doubt that the greatest challenge facing managers and researchers in the field of finance is the presence of uncertainty. Indeed risk, which arises from uncertainty, is fundamental to modern finance theory and, since its emergence as a separate discipline, much of the intellectual resources of the field have been devoted to risk analysis. The presence of risk, however, not only complicates decision financial making, it creates opportunities for reward for those who can analyze and manage risk effectively.

By and large, the evolution of commercial risk management technology has been characterized by computer technology lagging behind the theoretical advances of the field. As computers have become more powerful, they have permitted better testing and application of financial concepts. Large-scale implementation of Markowitz’s seminal ideas on portfolio management, for example, was held up for almost twenty years until sufficient computational speed and capacity were developed. Similarly, despite the overwhelming need from a conceptual viewpoint, daily marking to market of investment portfolios has only become a feature of professional funds management in the past decade or so, following advances in computer hardware and software.

Recent years have seen a broadening of the array of computer technologies applied to finance. One of the most exciting of these in terms of the potential for analyzing risk is Artificial Intelligence (AI). One of the contemporary methods of AI, Artificial Neural Networks (ANNs), in combination with other techniques, has recently begun to gain prominence as a potential tool in solving a wide variety of complex tasks. ANN-based commercial applications have been successfully implemented in fields ranging from medical to space exploration.

Files:

An Artificial Neural Networks Primer with Financial Applications Examples in Financial Distress Pred.pdf 442 kb

John Seekers 2016.09.16 03:13 #10

The main intention of this paper is to investigate, with new daily data, whether prices in the two Chinese stock exchanges (Shanghai and Shenzhen) follow a random-walk process as required by market efficiency. We use two different approaches, the standard variance-ratio test of Lo and MacKinlay (1988) and a model-comparison test that compares the ex post forecasts from a NAIVE model with those obtained from several alternative models (ARIMA, GARCH and Artificial Neural Network-ANN). To evaluate ex post forecasts, we utilize several procedures including RMSE, MAE, Theil's U, and encompassing tests. In contrast to the variance-ratio test, results from the model-comparison approach are quite decisive in rejecting the random-walk hypothesis in both Chinese stock markets. Moreover, our results provide strong support for the ANN as a potentially useful device for predicting stock prices in emerging markets.

Files:

On Testing the Random Walk Hypothesis - A Model-Comparison Approach.pdf 117 kb