Stock Price Prediction using Technical, Fundamental and News based Approach

Abstract

This paper presents the advanced method for stock price forecasting. Various technical, fundamental, and news-based methods are used to detect the stock price fluctuation and company profile. From the previous research, it is found that technical indicator like Stochastic Oscillator (KDJ), Moving Average Convergence Divergence (MACD), Bollinger Band (BB), and Relative Strength Index (RSI) are significant in predicting the stock price for a shorter run. But, it is challenging to detect the long-term price fluctuation using Technical data. To compensate for this problem, Fundamental or core data of the company can be collected and used along with technical data. Using the machine learning approach in this data leads to the possibility of getting an accurate prediction for guessing the stock price. Here, the pre-processing technique is applied on technical and fundamental data, to extract useful information then decision tree-based machine learning model is developed by using J48 with bagging to overcome data over fitting problem of J48 algorithm. Although this technique provides a good output, some flaws are there. If suddenly bad news about a particular company comes, then it will affect the price of the stock of that company. In such a condition, it will be very difficult to handle the system decision, so for such situations, news-based data mining can help to get company news. So that, suddenly fundamental changes can be handled. It is found that using the base factors of trading and stock price with news-based approach, deep-rooted stock price analysis is possible with a high accuracy rate.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 29 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.