Papers by Javad Khosravian
In contemporary times, as nancial content proliferates across the internet and social networks, a... more In contemporary times, as nancial content proliferates across the internet and social networks, accurately predicting future trends has become an everyday necessity for providing optimal investment strategies. Sentiment Analysis (SA), a prominent subject in arti cial intelligence, is pivotal in revealing people's emotions and opinions on speci c matters. This paper aims to leverage text-mining algorithms to categorize a text-based nancial dataset through sentiment analysis. Furthermore, a novel hybrid feature selection model is introduced to enhance the accuracy and performance when studying economic text. Initially, a widely recognized nancial text dataset (FiQA) was chosen. After applying preprocessing techniques encompassing data cleansing and feature extraction, the feature pool is reduced by utilizing ANOVA, RFI, and CHI2 algorithms. Subsequently, the features are re ned using the Particle Swarm Optimization (PSO) approach. In the subsequent stages, the text is classi ed by the Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), K-Nearest Neighbour (KNN), Naïve Bayes, and Support Vector Machine (SVM) algorithms, all of which yield notable performance outcomes. The results show that the ANOVA-PSO hybrid model for LSTM classi cation achieves an accuracy rate of 75%, superior to other Feature selection models.
Since the accuracy of corporate financial crisis prediction is very important for financial insti... more Since the accuracy of corporate financial crisis prediction is very important for financial institutions, investors and governments, many methods have been employed for developing effective prediction models. The aim of this research was twofold: (1) propose a new classification method following the artificial intelligence, which employs an Imperialist Competitive Algorithm (ICA) to the problem, (2) predict the financial crisis in Iranian firms listed inTehran stock exchange (TSE) using principal component analysis Imperialist Competitive Algorithm (PCAICA) model and its related financial ratios.For this purpose the sample was 60 registered firms in Tehran Stock Exchange and the financial information was gathered with use of their financial reports within 21 years beginning from 1991 and ending to 2012 and desired financial ratios were extracted. The experimental results show that the proposed model is good alternative for financial crisis prediction.
Since the accuracy of corporate financial crisis prediction is very important for financial insti... more Since the accuracy of corporate financial crisis prediction is very important for financial institutions, investors and governments, many methods have been employed for developing effective prediction models. The aim of this research was twofold:
Uploads
Papers by Javad Khosravian