Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userStock returns forecast: an examination by means of Artificial Neural Networks
74
0
0.0
(
0
)
Added by
Aurelio Fernandez Bariviera
Publication date
2018
fields
Financial
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
The validity of the Efficient Market Hypothesis has been under severe scrutiny since several decades. However, the evidence against it is not conclusive. Artificial Neural Networks provide a model-free means to analize the prediction power of past returns on current returns. This chapter analizes the predictability in the intraday Brazilian stock market using a backpropagation Artificial Neural Network. We selected 20 stocks from Bovespa index, according to different market capitalization, as a proxy for stock size. We find that predictability is related to capitalization. In particular, larger stocks are less predictable than smaller ones.
rate research
Read More
In recent years, hyperparameter optimization (HPO) has become an increasingly important issue in the field of machine learning for the development of more accurate forecasting models. In this study, we explore the potential of HPO in modeling stock returns using a deep neural network (DNN). The potential of this approach was evaluated using technical indicators and fundamentals examined based on the effect the regularization of dropouts and batch normalization for all input data. We found that the model using technical indicators and dropout regularization significantly outperforms three other models, showing a positive predictability of 0.53% in-sample and 1.11% out-of-sample, thereby indicating the possibility of beating the historical average. We also demonstrate the stability of the model in terms of the changes in its feature importance over time.
We extend the AROW regression algorithm developed by Vaits and Crammer in [VC11] to handle synchronous mini-batch updates and apply it to stock return prediction. By design, the model should be more robust to noise and adapt better to non-stationarity compared to a simple rolling regression. We empirically show that the new model outperforms more classical approaches by backtesting a strategy on S&P500 stocks.
Artificial neural networks (ANNs) have recently also been applied to solve partial differential equations (PDEs). In this work, the classical problem of pricing European and American financial options, based on the corresponding PDE formulations, is studied. Instead of using numerical techniques based on finite element or difference methods, we address the problem using ANNs in the context of unsupervised learning. As a result, the ANN learns the option values for all possible underlying stock values at future time points, based on the minimization of a suitable loss function. For the European option, we solve the linear Black-Scholes equation, whereas for the American option, we solve the linear complementarity problem formulation. Two-asset exotic option values are also computed, since ANNs enable the accurate valuation of high-dimensional options. The resulting errors of the ANN approach are assessed by comparing to the analytic option values or to numerical reference solutions (for American options, computed by finite elements).
The aim of this study is to investigate quantitatively whether share prices deviated from company fundamentals in the stock market crash of 2008. For this purpose, we use a large database containing the balance sheets and share prices of 7,796 worldwide companies for the period 2004 through 2013. We develop a panel regression model using three financial indicators--dividends per share, cash flow per share, and book value per share--as explanatory variables for share price. We then estimate individual company fundamentals for each year by removing the time fixed effects from the two-way fixed effects model, which we identified as the best of the panel regression models. One merit of our model is that we are able to extract unobservable factors of company fundamentals by using the individual fixed effects. Based on these results, we analyze the market anomaly quantitatively using the divergence rate--the rate of the deviation of share price from a companys fundamentals. We find that share prices on average were overvalued in the period from 2005 to 2007, and were undervalued significantly in 2008, when the global financial crisis occurred. Share prices were equivalent to the fundamentals on average in the subsequent period. Our empirical results clearly demonstrate that the worldwide stock market fluctuated excessively in the time period before and just after the global financial crisis of 2008.
In this study, we investigate the statistical properties of the returns and the trading volume. We show a typical example of power-law distributions of the return and of the trading volume. Next, we propose an interacting agent model of stock markets inspired from statistical mechanics [24] to explore the empirical findings. We show that as the interaction among the interacting traders strengthens both the returns and the trading volume present power-law behavior.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
