Financial news recommendation based on graph embeddings

In the financial services industry, it is crucial for analysts to constantly monitor and stay informed on the latest developments of their portfolio of companies. This ensures that analysts are up-to-date in their analysis and provide highly credible and timely insights. Currently, analysts receive news alerts through manually created news alert subscriptions that are often noisy and difficult to manage. The manual review process is time-consuming and error-prone. We demonstrate Discovery News, a framework for an automated news recommender system for financial analysis at S&P's Global Ratings. This system includes the automated ingestion, relevancy, clustering, and ranking of news. The proposed framework is adaptable to any form of input news data and can seamlessly integrate with other data used for analysis like financial data.

Download Full-text

Personalized Financial News Recommendation Algorithm Based on Ontology

Procedia Computer Science ◽

10.1016/j.procs.2015.07.151 ◽

2015 ◽

Vol 55 ◽

pp. 843-851 ◽

Cited By ~ 5

Author(s):

Rui Ren ◽

Lingling Zhang ◽

Limeng Cui ◽

Bo Deng ◽

Yong Shi

Keyword(s):

Recommendation Algorithm ◽

Financial News ◽

News Recommendation

Download Full-text

News recommendation system using machine learning

International Journal of Engineering & Technology ◽

10.14419/ijet.v7i2.27.11748 ◽

2018 ◽

Vol 7 (2.18) ◽

pp. 32

Author(s):

Neha Rani ◽

Sudhir Sudhir Pathak

Keyword(s):

Neural Network ◽

Recommendation System ◽

High Accuracy ◽

Svm Classifier ◽

Financial News ◽

The Neural Network ◽

Market Forecast ◽

News Recommendation ◽

Weighted Values ◽

The Given

The forecasting of financial news is yet becoming the main issue to divide the new into different classes on the basis of present time series. Moreover, it might be utilized for predicting and analyzing the stock market for the particular industry. Thus, the new content is significantly important to influence market forecast report. In this paper, the financial news from four countries namely America, Australia, India and South Africa along with their stop words are consider. The words along with their weighted values are determined and then the neural network is trained. Here, artificial neural network is used for classifying the appropriate results for the given input data. At last the comparison of ANN with SVM is shown. Experiments show that the ANN classification provides high accuracy to predict the news than the SVM classifier.

Download Full-text