Forecasting Stock Indices: A Comparison of Classification and Level Estimation Models

By Mark T. Leung, Hazem Daouk, An-Sing Chen. 1999

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Statistical Arbitrage in Cryptocurrency Markets (2019, background): “This approach is promising, as classiﬁcation problems have found to work better than regression problems in the context of ﬁnancial market predictions (Enke and Thawornwong 2005; Leung et al. 2000).”
Classification-based financial markets prediction using deep neural networks (2016, neutral): “More recently, however, Leung et al. (2000) provide evidence that classiﬁcation based methods outperform level based meth-ods in the prediction of the direction of stock movement and trading returns maximization.”
Financial time series forecasting with machine learning techniques: a survey (2010, background): “Others 10 [4], [5], [15], [17], [20], [26], [35], [38], [39], [41] Table 3: Reviewed papers classified by input variables”
The use of data mining and neural networks for forecasting stock market returns (2005, background): “This result supports the findings of Leung et al. (2000) that the classification models can generate higher profits than the level estimation models on the S&P 500 index trading.”
Forecasting East Asian Indices Futures via a Novel Hybrid of Wavelet-PCA Denoising and Artificial Neural Network Models (2016, background): “In addition to that, Leung [70] achieved 17.”
A High Frequency Trade Execution Model for Supervised Learning (2017, unknown): “Sequence classiﬁcation has been considered elsewhere in the literature for lower frequency price movement prediction from historical prices (Leung et al., 2000; Dixon et al., 2016).”
Evolving Least Squares Support Vector Machines for Stock Market Trend Mining (2009, methodology): “The BPNN model [4] is widely used and produces successful learning and generalization results in various research areas.”
Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500 (2017, methodology): “We construct a classiﬁcation instead of a regression problem, as the literature suggests that the former performs better than the latter in predicting ﬁnancial market data (Leung et al., 2000; Enke and Thawornwong, 2005).”
Sequence classification of the limit order book using recurrent neural networks (2017, background): “Sequence classification has been considered elsewhere in the literature for lower frequency price movement prediction from historical prices (Leung et al., 2000; Dixon et al., 2016).”
Predicting direction of stock price index movement using artificial neural networks and support vector machines: The sample of the Istanbul Stock Exchange (2011, methodology): “Accurate predictions of movement of stock price indexes are very important for developing effective market trading strategies (Leung, Daouk, & Chen, 2000).”