|
on Big Data |
| By: | Zeya Zhang; Weizheng Chen; Hongfei Yan |
| Abstract: | This paper proposed a method for stock prediction. In terms of feature extraction, we extract the features of stock-related news besides stock prices. We first select some seed words based on experience which are the symbols of good news and bad news. Then we propose an optimization method and calculate the positive polar of all words. After that, we construct the features of news based on the positive polar of their words. In consideration of sequential stock prices and continuous news effects, we propose a recurrent neural network model to help predict stock prices. Compared to SVM classifier with price features, we find our proposed method has an over 5% improvement on stock prediction accuracy in experiments. |
| Date: | 2017–07 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1707.07585&r=big |
| By: | David W. Lu |
| Abstract: | With the breakthrough of computational power and deep neural networks, many areas that we haven't explore with various techniques that was researched rigorously in past is feasible. In this paper, we will walk through possible concepts to achieve robo-like trading or advising. In order to accomplish similar level of performance and generality, like a human trader, our agents learn for themselves to create successful strategies that lead to the human-level long-term rewards. The learning model is implemented in Long Short Term Memory (LSTM) recurrent structures with Reinforcement Learning or Evolution Strategies acting as agents The robustness and feasibility of the system is verified on GBPUSD trading. |
| Date: | 2017–07 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1707.07338&r=big |
| By: | Esra Ball? (Çukurova University); Salih Çam (Çukurova University); Müge Manga (Çukurova University); Çiler Sigeze (Çukurova University) |
| Abstract: | This study investigates the relationship between energy use, GDP, carbon dioxide emissions, population, financial development, and industrialization utilizing ARDL and artificial neural network for Turkey. The data covers the period from 1968 to 2013. The study performed a two stage analysis. At the first stage, we examined the long run relationship and causality between variables. The variables are found to be cointegrated. The Granger causality test results shows that there is a unidirectional causality running from energy use to both carbon dioxide emissions and industrialization. According to the artificial neural network results, the most important effect on energy use comes from GDP. The predicted energy use from 1968 to 2013 has maximum absolute error of % 11. 31 and minimum absolute error of %0.07. Neural network evidence shows that the R-square coefficient is 98% for the sample period. |
| Keywords: | Energy use, ARDL, Neural network, Turkey |
| JEL: | C10 Q43 C22 |
| Date: | 2017–07 |
| URL: | http://d.repec.org/n?u=RePEc:sek:iacpro:4607826&r=big |