The Internet provides the opportunity for investors to post online opinions that they share with fellow investors Sentiment analysis of online opinion posts can facilitate both investors' investment decision making and stock companies' risk perception This paper develops a novel sentiment ontology to conduct context-sensitive sentiment analysis of online opinion posts in stock markets The methodology integrates popular sentiment analysis into machine learning approaches based on support vector machine and generalized autoregressive conditional heteroskedasticity modeling A typical financial website called Sina Finance has been selected as an experimental platform where a corpus of financial review data was collected Empirical results suggest solid correlations between stock price volatility trends and stock forum sentiment Computational results show that the statistical machine learning approach has a higher classification accuracy than that of the semantic approach Results also imply that investor sentiment has a particularly strong effect for value stocks relative to growth stocks

A Decision Support Approach for Online Stock Forum Sentiment Analysis

On neural networks and learning systems for business computing

Mold contamination of grains not only contributes to inedible food, resulting in economic losses, but also leads to mold in humans and livestock, and can even be carcinogenic to them. Rice, as one of the main grain varieties, if stored improperly, is easily susceptible to mildew. In order to detect the total number of mold colonies in rice more accurately, a method based on hyperspectral imaging technology was investigated.; Results: In this paper, non-destructive detection for the total number of mold colonies in rice was performed from the angle of spectral analysis. A determination coefficient of 0.9621 for the calibration set and 0.9511 for the prediction set between the spectral data and number of mold colonies were eventually achieved by establishing the best support vector regression (SVR) model, optimized by the Gray Wolf Optimization (GWO) algorithm.; Conclusion: Hyperspectral imaging technology combined with the optimal model (GWO-SVR) is feasible for non-destructive detection of the total number of mold colonies in rice, providing a promising tool for the mold detection of other agricultural products. © 2017 Society of Chemical Industry.; © 2017 Society of Chemical Industry.

Non-destructive detection for mold colonies in rice based on hyperspectra and GWO-SVR.

Forecasting daily and monthly streamflows is necessary for short- and long-term water resources management, particularly in extreme cases, e.g., flood and drought. Accurate models are needed to plan and manage water resources in watersheds. Recently, support vector regression (SVR) shows the ability to handle the hydrological forecasting issues, but the accuracy of SVR depends on the appropriate choice of parameters and selection of proper inputs. A new meta-heuristic algorithm called grey wolf optimizer (GWO) is used in the current research in order to improve SVR accuracy in forecasting monthly streamflow. The proposed approach is compared with other evolutionary methods, particle swarm optimization, shuffled complex evolution, and multi-verse optimization, that are employed in tuning SVR parameters. Furthermore, the proposed methods were also combined with wavelet transform and tested using monthly streamflow data from two gauging stations, Ain Bedra and Fermatou, in Algeria. To assess the performance of the developed models, Nash–Sutcliffe efficiency (NSE), correlation coefficient, root mean squared error (RMSE), and mean absolute error (MAE) were used. The obtained results indicate that multi-linear regression provides appropriate input variables to SVR models. According to all of the performance measures used, hybrid models exhibit better performances, in monthly streamflow prediction, compared with single versions. For example, for the Ain Bedra station, the NSEcriterion and the correlation coefficient values increased considerably from 27.36% and 0.5405, for the single models, to 95.72% and 0.9786, for the hybrid models. A great decrease has also been obtained for the RMSE and MAE values, which decreased from 0.1562 m3/s and 0.1244 m3/s to 0.6433m3/s and 0.3047 m3/s. In addition, the new GWO algorithm outperformed the other algorithms in terms of both forecasting accuracy and convergence.

A new intelligent method for monthly streamflow prediction: hybrid wavelet support vector regression based on grey wolf optimizer (WSVR–GWO)

Labor votes with its feet-individuals migrate from areas of low wages to areas of higher wages. That has been the traditional view, one that has spawned much policy advice to control migration and to affect the location decisions of migrant laborers. But recent research indicates that portfolio investment theory might hold the key to understanding why people migrate in developing economies and how and why they remit their earnings. Under this theory, migration decisions are ordered by family needs for stable income levels, provided by a diversified portfolio of laborers, both male and female, and the need to jointly insure the family's well-being. In brief, group decisionmaking and objectives, rather than the wishes of individual migrants, determine migration patterns and remittance flows. This article, based on recent and earlier research by the author and his colleagues, attempts to explain migrant behavior in light of portfolio investment theory applied to field studies conducted in different parts of the world (see box on research). The results of the studies suggest a re-evaluation of policy approaches to migration and remittance issues.

Migration in LDCs: Risk, Remittances, and the Family

The use of GARCH type models and computational-intelligence-based techniques for forecasting financial time series has been proved extremely successful in recent times. In this article, we apply the finite mixture of ARMA-GARCH model instead of AR or ARMA models to compare with the standard BP and SVM in forecasting financial time series (daily stock market index returns and exchange rate returns). We do not apply the pure GARCH model as the finite mixture of the ARMA-GARCH model outperforms the pure GARCH model. These models are evaluated on five performance metrics or criteria. Our experiment shows that the SVM model outperforms both the finite mixture of ARMA-GARCH and BP models in deviation performance criteria. In direction performance criteria, the finite mixture of ARMA-GARCH model performs better. The memory property of these forecasting techniques is also examined using the behavior of forecasted values vis-a-vis the original values. Only the SVM model shows long memory property in forecasting fi...

Comparison of the finite mixture of ARMA-GARCH, back propagation neural networks and support-vector machines in forecasting financial returns

In the recent years, the use of GARCH type (especially, ARMA-GARCH) models and computational-intelligence-based techniques—Support Vector Machine (SVM) and Relevance Vector Machine (RVM) have been successfully used for financial forecasting. This paper deals with the application of ARMA-GARCH, recurrent SVM (RSVM) and recurrent RVM (RRVM) in volatility forecasting. Based on RSVM and RRVM, two GARCH methods are used and are compared with parametric GARCHs (Pure and ARMA-GARCH) in terms of their ability to forecast multi-periodically. These models are evaluated on four performance metrics: MSE, MAE, DS, and linear regression R squared. The real data in this study uses two Asian stock market composite indices of BSE SENSEX and NIKKEI225. This paper also examines the effects of outliers on modeling and forecasting volatility. Our experiment shows that both the RSVM and RRVM perform almost equally, but better than the GARCH type models in forecasting. The ARMA-GARCH model is superior to the pure GARCH and only the RRVM with RSVM hold the robustness properties in forecasting.

/pdf/recurrent-support-and-relevance-vector-machines-based-model-3avx214zsz.pdf

Recurrent Support and Relevance Vector Machines Based Model with Application to Forecasting Volatility of Financial Returns

This article applied GARCH model instead AR or ARMA model to compare with the standard BP and SVM in forecasting of the four international including two Asian stock markets indices.These models were evaluated on five performance metrics or criteria. Our experimental results showed the superiority of SVM and GARCH models, compared to the standard BP in forecasting of the four international stock markets indices.

/pdf/comparison-of-garch-neural-network-and-support-vector-2tine3nezr.pdf

Comparison of GARCH, Neural Network and Support Vector Machine in Financial Time Series Prediction

Many researchers have already published huge number of papers comparing Autoregressive (AR) model, a model based on Box-Jenkins methodology, and Back Propagation Artificial Neural Network (BPANN) in financial time-series forecasting. Among them, some compared SVMs and BPs taking AR as a benchmark in forecasting the six major Asian stock markets. They showed that both the SVMs and BPs outperform the traditional models, ARs. They did prediction of transformed data, but not level data. They did not take account of GARCH model, specially developed to model financial time series. Generalized Autoregressive Conditional Heteroskedastic (GARCH) model is needed to capture high volatility for better forecasts. This article applies GARCH model instead AR or ARMA model to compare with standard BP in forecasting of the four international including two Asian stock markets indices. Our fitted GARCH models give better forecasts than the fitted standard BP models in forecasting of the four international markets indices except one market.

Comparison of GARCH and neural network methods in financial time series prediction

To understand the finance-growth nexus, this paper is intended to find a fewer number of important financial factors using Factor Analysis on some selected indicators of Bangladesh financial sector during the period 1988-2013. This paper then tries to check whether the identified financial factors cause economic growth or economic growth causes financial factors using the Granger – Causality test. Factor Analysis shows that financial indicators under the dimensions, depth and stability form Factor 1, and the indicators under the dimensions, use/access and efficiency form Factor 2. Being consistent with economic sense, Granger – Causality test shows that no financial factor significantly causes economic growth; rather economic growth causes “depth/stability” (‘private credit + capitalization’ /non-performing loan) factor of financial sector during the period. In summary, on average, financial sector of Bangladesh is being unstably (being increased non-performing loan) deepened with response to the demand of economic growth since 1988.

/pdf/financial-sector-development-and-economic-growth-in-khsv5bfhmr.pdf

Altaf Hossain

Papers

Comparison of the finite mixture of ARMA-GARCH, back propagation neural networks and support-vector machines in forecasting financial returns

Recurrent Support and Relevance Vector Machines Based Model with Application to Forecasting Volatility of Financial Returns

Comparison of GARCH, Neural Network and Support Vector Machine in Financial Time Series Prediction

Comparison of GARCH and neural network methods in financial time series prediction

Financial Sector Development and Economic Growth in Bangladesh: A Factor Analysis Based Causality Approach