Achilleas Zapranis

Stock performance modeling using neural networks: a comparative study with regression models

Abstract We examine the use of neural networks as an alternative to classical statistical techniques for forecasting within the framework of the APT (arbitrage pricing theory) model for stock ranking. We show that neural networks outperform these statistical techniques in forecasting accuracy terms, and give better model fitness in-sample by one order of magnitude. We identify intervals for the network parameter values for which these performance figures are statistically stable. Neural networks have been criticised for not being able to provide an explanation of how they interact with their environment and how they reach an outcome. We show that by using sensitivity analysis, neural networks can provide a reasonable explanation of their predictive behaviour and can model their environment more convincingly than regression models.

Principles of Neural Model Identification, Selection and Adequacy

1 Introduction.- 2 Neural Model Identification.- 3 Review of Current Practice in Neural Model Identification.- 4 Neural Model Selection: the Minimum Prediction Risk Principle.- 5 Variable Significance Testing: a Statistical Approach.- 6 Model Adequacy Testing.- 7 Neural Networks in Tactical Asset Allocation: a Case Study.- 8 Conclusions.- Appendices.- A Computation of Network Derivatives.- B Generating Random Normal Deviates.- References.

Neural model identification, variable selection and model adequacy

In recent years an impressive array of publications has appeared claiming considerable successes of neural networks in modelling financial data but sceptical practitioners and statisticians are still raising the question of whether neural networks really are ‘a major breakthrough or just a passing fad’. A major reason for this is the lack of procedures for performing tests for misspecified models, and tests of statistical significance for the various parameters that have been estimated, which makes it difficult to assess the models significance and the possibility that any short-term successes that are reported might be due to ‘data mining’. In this paper we describe a methodology for neural model identification which facilitates hypothesis testing at two levels: model adequacy and variable significance. The methodology includes a model selection procedure to produce consistent estimators, a variable selection procedure based on statistical significance and a model adequacy procedure based on residuals analysis. We propose a novel, computationally efficient scheme for estimating sampling variability of arbitrarily complex statistics for neural models and apply it to variable selection. The approach is based on sampling from the asymptotic distribution of the neural models parameters (‘parametric sampling’). Controlled simulations are used for the analysis and evaluation of our model identification methodology. A case study in tactical asset allocation is used to demonstrate how the methodology can be applied to real-life problems in a way analogous to stepwise forward regression analysis. Neural models are contrasted to multiple linear regression. The results indicate the presence of non-linear relationships in modelling the equity premium. Copyright

Modelling the Temperature Time-dependent Speed of Mean Reversion in the Context of Weather Derivatives Pricing

In this paper, in the context of an Ornstein–Uhlenbeck temperature process, we use neural networks to examine the time dependence of the speed of the mean reversion parameter α of the process. We estimate non‐parametrically with a neural network a model of the temperature process and then compute the derivative of the network output w.r.t. the network input, in order to obtain a series of daily values for α. To our knowledge, this is the first time that this has been done, and it gives us a much better insight into the temperature dynamics and temperature derivative pricing. Our results indicate strong time dependence in the daily values of α, and no seasonal patterns. This is important, since in all relevant studies performed thus far, α was assumed to be constant. Furthermore, the residuals of the neural network provide a better fit to the normal distribution when compared with the residuals of the classic linear models used in the context of temperature modelling (where α is constant). It follows that by setting the mean reversion parameter to be a function of time we improve the accuracy of the pricing of the temperature derivatives. Finally, we provide the pricing equations for temperature futures, when α is time dependent.

Financial time series modelling with discounted least squares backpropagation

Abstract We propose a simple modification to the error backpropagation procedure which takes into account gradually changing input-output relations. The procedure is based on the principle of Discounted least squares whereby learning is biased towards more recent observations with long term effects experiencing exponential decay through time. This is particularly important in systems in which the structural relationship between input and response vectors changes gradually over time but certain elements of long term memory are still retained. The procedure is implemented by a simple modification of the least-squares cost function commonly used in error backpropagation. We compare the performance of the two cost functions using both a controlled simulation experiment and a non-trivial application in estimating stock returns on the basis of multiple factor exposures. We show that in both cases the DLS procedure gives significantly better results. Typically, there is an average improvement of above 30% (in MSE terms) for the stock return modelling problem.

Weather derivatives pricing: Modeling the seasonal residual variance of an Ornstein-Uhlenbeck temperature process with neural networks

In this paper, we use neural networks in order to model the seasonal component of the residual variance of a mean-reverting Ornstein-Uhlenbeck temperature process, with seasonality in the level and volatility. This approach can be easily used for pricing weather derivatives by performing Monte Carlo simulations. Moreover, in synergy with neural networks we use wavelet analysis to identify the seasonality component in the temperature process as well as in the volatility of the temperature anomalies. Our model is validated on more than 100 years of data collected from Paris, one of the European cities traded at Chicago Mercantile Exchange. Our results show a significant improvement over more traditional alternatives, regarding the statistical properties of the temperature process. This is important since small misspecifications in the temperature process can lead to large pricing errors.

External security determinants of Greek military expenditure: An empirical investigation using Neural networks

Greece has regularly ranked as the country with the highest defence burden in NATO and the European Union. Over the past decades she has allocated an averatge 6% of GDP to defence yearly. This study using neural networks examines the external security determinants of Greek military expenditure in the context of the ongoing Greek‐Turkish conflict.

Introduction to Stochastic Calculus

The purpose of this chapter is to give the necessary background in stochastic calculus. It is not meant to provide a complete background in stochastic theory but rather present all the necessary theorems and results that will be used later on in order to derive the prices of various weather derivatives on different weather indexes. The reader, familiar or not to stochastic calculus, may use this chapter as a reference.

A novel, rule-based technical pattern identification mechanism: Identifying and evaluating saucers and resistant levels in the US stock market

This paper has two main purposes. The first one is the development of a rigorous rule-based mechanism for identifying the rounding bottoms (also known as saucers) pattern and resistant levels. The design of this model is based solely on principles of technical analysis, and thus making it a proper system for evaluating the efficacy of the aforementioned technical trading patterns. The second aim of this paper is measuring the predictive power of buy-signals generated by these technical patterns. Empirical results obtained from seven US tech stocks indicate that simple resistant levels outperform saucers patterns. Furthermore, positive statistical significant excess returns are being generated only in first sub-periods of examination. These returns decline or even vanish as the experiment proceeds to recent years. Our findings are aligned with the results reported by various former studies. The proposed identification mechanism can be used as a component of an expert system to assist academic community in evaluating trading strategies where technical patterns are embedded.

Wavelet Neural Networks: With Applications in Financial Engineering, Chaos, and Classification

A step-by-step introduction to modeling, training, and forecasting using wavelet networksWavelet Neural Networks: With Applications in Financial Engineering, Chaos, and Classification presents the statistical model identification framework that is needed to successfully apply wavelet networks as well as extensive comparisons of alternate methods. Providing a concise and rigorous treatment for constructing optimal wavelet networks, the book links mathematical aspects of wavelet network construction to statistical modeling and forecasting applications in areas such as finance, chaos, and classification.The authors ensure that readers obtain a complete understanding of model identification by providing in-depth coverage of both model selection and variable significance testing. Featuring an accessible approach with introductory coverage of the basic principles of wavelet analysis, Wavelet Neural Networks: With Applications in Financial Engineering, Chaos, and Classification also includes: Methods that can be easily implemented or adapted by researchers, academics, and professionals in identification and modeling for complex nonlinear systems and artificial intelligence Multiple examples and thoroughly explained procedures with numerous applications ranging from financial modeling and financial engineering, time series prediction and construction of confidence and prediction intervals, and classification and chaotic time series prediction An extensive introduction to neural networks that begins with regression models and builds to more complex frameworks Coverage of both the variable selection algorithm and the model selection algorithm for wavelet networks in addition to methods for constructing confidence and prediction intervalsIdeal as a textbook for MBA and graduate-level courses in applied neural network modeling, artificial intelligence, advanced data analysis, time series, and forecasting in financial engineering, the book is also useful as a supplement for courses in informatics, identification and modeling for complex nonlinear systems, and computational finance. In addition, the book serves as a valuable reference for researchers and practitioners in the fields of mathematical modeling, engineering, artificial intelligence, decision science, neural networks, and finance and economics.