دانلود رایگان مقاله انگلیسی پیش بینی قیمت سهام مبتنی بر ردیابی الگو با استفاده از داده های بزرگ - الزویر 2018

عنوان فارسی
پیش بینی قیمت سهام مبتنی بر ردیابی الگو با استفاده از داده های بزرگ
عنوان انگلیسی
Pattern graph tracking-based stock price prediction using big data
صفحات مقاله فارسی
0
صفحات مقاله انگلیسی
46
سال انتشار
2018
نشریه
الزویر - Elsevier
فرمت مقاله انگلیسی
PDF
کد محصول
E8622
رشته های مرتبط با این مقاله
علوم اقتصادی
گرایش های مرتبط با این مقاله
اقتصادسنجی، اقتصاد مالی و اقتصاد پولی
مجله
نسل آینده سیستم های کامپیوتری - Future Generation Computer Systems
دانشگاه
BK21PLUS Creative Human Resource Development Program for IT Convergence - Pusan National University - South Korea
کلمات کلیدی
پیش بینی قیمت سهام، انحراف زمان دینامیکی، انتخاب ویژگی، شبکه عصبی مصنوعی، فاصله Jaro-Winkler، تقریب مجموع نمادین
چکیده

Abstract


Stock price forecasting is the most difficult field owing to irregularities. However, because stock prices sometimes show similar patterns and are determined by a variety of factors, we propose determining similar patterns in historical stock data to achieve daily stock prices with high prediction accuracy and potential rules for selecting the main factors that significantly affect the price, while simultaneously considering all factors. This study is intended at suggesting a new complex methodology that finds the optimal historical dataset with similar patterns according to various algorithms for each stock item and provides a more accurate prediction of daily stock price. First, we use a Dynamic Time Warping algorithm to find patterns with the most similar situation adjacent to a current pattern. Second, we select the determinants most affected by the stock price using feature selection based on Stepwise Regression Analysis. Moreover, we generate an artificial neural network model with selected features as training data for predicting the best stock price. Finally, we use Jaro-Winkler distance with Symbolic Aggregate approXimation (SAX) as a prediction accuracy measure to verify the accuracy of our model.

نتیجه گیری

9. Conclusion and future work


In this paper, we determined that stock prices sparsely show similar patterns and all the variables do not have a significant impact on the price. For short-term prediction, we proposed a novel method based on the combination of dynamic time warping, stepwise regression, and artificial neural network model to find similar historical datasets for each stock item and predict daily stock price using optimal significant variables through feature selection and comparison of leverage. Moreover, we dealt with the overall process using a big data processing framework composed of Hadoop, R, and RHive. Finally, we demonstrated the prediction accuracy for three stock items using SAX and Jaro-Winkler distance. In future work, we will improve the reliability of the predicted stock price by relation analysis of same field for a longer period and enhance the execution time by changing our system or file structure to use minimum search queries.


بدون دیدگاه