Forecasting futures trading volume using neural networks

By Iebeling Kaastra, Milton S. Boyd. 1995

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

Classification-based financial markets prediction using deep neural networks (2016, neutral): “Traditionally, researchers will iteratively experiment with a handful of signals to train a level based method, such as vector autoregres-sion, for each instrument (see for example Kaastra and Boyd (1995); Refenes (1994); Trippi and DeSieno (1992)).”
Intelligent technical analysis based equivolume charting for stock trading using neural networks (2008, background): “Studies have been made to examine the role of trading volume in an area of stock market prediction and investment (Blume et al., 1994; Campbell, Grossman, & Wang, 1993; Kaastra & Boyd, 1995; Lee & Swaminathan, 2000).”
Application of support vector machines in !nancial time series forecasting (2001, background): “So neural networks are more powerful in describing the dynamics of ÿnancial time series in comparison to traditional statistical models [7] [8] [9].”
Support vector machine with adaptive parameters in financial time series forecasting (2003, background): “neural networks are more powerful in describing the dynamics of financial time series in comparison to traditional statistical models [10]–[12].”
Forecasting volatility and volume in the Tokyo stock market: Long memory, fractality and regime switching (2007, background): “Models The empirical finance literature has mainly concentrated on trying to predict returns and volatility, but has hardly paid any attention to volume: a search for pertinent contributions in the literature has brought about only one single entry, Kaastra and Boyd (1995).”
Ratio-based lengths of intervals to improve fuzzy time series forecasting (2006, methodology): “Furthermore, various studies have suggested that Theil’s U statistic can be used to compare the forecasting series with naïve models [2] and [15].”
Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications (2000, background): “As in any prediction/forecasting model, the selection of appropriate model inputs is extremely important (Faraway and Chatﬁeld, 1998; Kaastra and Boyd, 1995).”
Prediction of Soil Organic Carbon across Different Land‐use Patterns (2005, background): “Ep 1 2 L k 1 (yk Ok)2 [7] Selection of Inputs Selection of model inputs plays an important role in develRMSE √ 1 2 L k 1 (yk Ok)2 [8] oping predictive models (Faraway and Chatfield, 1998; Kaastra and Boyd, 1995).”
Modified support vector machines in financial time series forecasting (2002, background): “So neural networks are less susceptible to the model mis-speci cation problem than most of the parametric models, and they are more powerful in describing the dynamics of nancial time series than traditional statistical models [1,7,24].”
A neural network approach for attenuation relationships: An application using strong ground motion data from Turkey (2007, methodology): “Even though the selection of the algorithm inputs and outputs is one of the most significant impacts on model performance (Kaastra and Boyd, 1995), they have already been assigned for the networks of this study as compatible with attenuation equations.”
Sequence classification of the limit order book using recurrent neural networks (2017, methodology): “The application of artiﬁcial neural networks (ANNs) to uni-variate ﬁnancial time series methods are well documented (Faraway and Chatﬁeld, 1998; Refenes, 1994; Trippi and DeSieno, 1992; Kaastra and Boyd, 1995).”