ترغب بنشر مسار تعليمي؟ اضغط هنا

Evaluating data augmentation for financial time series classification

257   0   0.0 ( 0 )
 نشر من قبل Elizabeth Fons
 تاريخ النشر 2020
والبحث باللغة English




اسأل ChatGPT حول البحث

Data augmentation methods in combination with deep neural networks have been used extensively in computer vision on classification tasks, achieving great success; however, their use in time series classification is still at an early stage. This is even more so in the field of financial prediction, where data tends to be small, noisy and non-stationary. In this paper we evaluate several augmentation methods applied to stocks datasets using two state-of-the-art deep learning models. The results show that several augmentation methods significantly improve financial performance when used in combination with a trading strategy. For a relatively small dataset ($approx30K$ samples), augmentation methods achieve up to $400%$ improvement in risk adjusted return performance; for a larger stock dataset ($approx300K$ samples), results show up to $40%$ improvement.



قيم البحث

اقرأ أيضاً

Financial time series have been investigated to follow fat-tailed distributions. Further, an empirical probability distribution sometimes shows cut-off shapes on its tails. To describe this stylized fact, we incorporate the cut-off effect in supersta tistics. Then we confirm that the presented stochastic model is capable of describing the statistical properties of real financial time series. In addition, we present an option pricing formula with respect to superstatistics.
The application of deep learning to time series forecasting is one of the major challenges in present machine learning. We propose a novel methodology that combines machine learning and image processing methods to define and predict market states wit h intraday financial data. A wavelet transform is applied to the log-return of stock prices for both image extraction and denoising. A convolutional neural network then extracts patterns from denoised wavelet images to classify daily time series, i.e. a market state is associated with the binary prediction of the daily close price movement based on the wavelet image constructed from the price changes in the first hours of the day. This method overcomes the low signal-to-noise ratio problem in financial time series and gets a competitive prediction accuracy of the market states Up and Down of financial data as tested on the S&P 500.
Forecasting stock returns is a challenging problem due to the highly stochastic nature of the market and the vast array of factors and events that can influence trading volume and prices. Nevertheless it has proven to be an attractive target for mach ine learning research because of the potential for even modest levels of prediction accuracy to deliver significant benefits. In this paper, we describe a case-based reasoning approach to predicting stock market returns using only historical pricing data. We argue that one of the impediments for case-based stock prediction has been the lack of a suitable similarity metric when it comes to identifying similar pricing histories as the basis for a future prediction -- traditional Euclidean and correlation based approaches are not effective for a variety of reasons -- and in this regard, a key contribution of this work is the development of a novel similarity metric for comparing historical pricing data. We demonstrate the benefits of this metric and the case-based approach in a real-world application in comparison to a variety of conventional benchmarks.
A well-interpretable measure of information has been recently proposed based on a partition obtained by intersecting a random sequence with its moving average. The partition yields disjoint sets of the sequence, which are then ranked according to the ir size to form a probability distribution function and finally fed in the expression of the Shannon entropy. In this work, such entropy measure is implemented on the time series of prices and volatilities of six financial markets. The analysis has been performed, on tick-by-tick data sampled every minute for six years of data from 1999 to 2004, for a broad range of moving average windows and volatility horizons. The study shows that the entropy of the volatility series depends on the individual market, while the entropy of the price series is practically a market-invariant for the six markets. Finally, a cumulative information measure - the `Market Heterogeneity Index- is derived from the integral of the proposed entropy measure. The values of the Market Heterogeneity Index are discussed as possible tools for optimal portfolio construction and compared with those obtained by using the Sharpe ratio a traditional risk diversity measure.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا