Data Mining on Romanian Stock Market Using Neural Networks for Price Prediction

Abstract

Predicting future prices by using time series forecasting models has become a relevant trading strategy for most stock market players. Intuition and speculation are no longer reliable as many new trading strategies based on artificial intelligence emerge. Data mining represents a good source of information, as it ensures data processing in a convenient manner. Neural networks are considered useful prediction models when designing forecasting strategies. In this paper we present a series of neural networks designed for stock exchange rates forecasting applied on three Romanian stocks traded on the Bucharest Stock Exchange (BSE). A multistep ahead strategy was used in order to predict short-time price fluctuations. Later, the findings of our study can be integrated with an intelligent multi-agent system model which uses data mining and data stream processing techniques for helping users in the decision making process of buying or selling stocks.

Intelligent agent-assisted organizational memory in knowledge management systems

“…IAs do not normally lose their memories and continually learn from every financial transaction that they perform as their knowledge base grows and establishes sustainable protocols for data management (Grabowski et al, 2018). Further, intelligent multi-agent system models use "data mining and data stream processing techniques for helping users in the decision process of buying or selling stocks" (p. 125) (Nemes and Butoi, 2013) and assist in other financial decision-making, such as credit scoring (Yu et al, 2009). These source and user layers of knowledge acquired are increasingly used for application and usage in the memory and KM systems.…”

Experimen Data Cuaca BMKG untuk Memprediksi Potensi Energi Alternativ Tenaga Angin di Kota Bandar Lampung

“…Prediksi atau biasa disebut forecasting merupakan metode data mining yang bertujuan memperkirakan nilai dari atribut tertentu pada masa yang akan datang dengan memperhatikan data sebelumnya yang bersifat time series (berdasarkan waktu). Kajian mengenai forecasting pada data mining sudah pernah dilakukan, dan salah satu pendekatan yang banyak digunakan menggunakan algoritma Multilayer Perceptron (MLP) [4,5,6,7]. Algoritma MLP merupakan variasi dari Artificial Neural Network (ANN) dengan kelebihan yang mendukung proses forecasting seperti bersifat umum dan fleksibel serta robust terhadap data yang bersifat nonlinier dengan distribusi yang tidak normal [6].…”

Supervised Support Vector Machine in Predicting Foreign Exchange Trading

“…The disadvantage of this model is simple as well as using of small data set for the experiments so that the quick regression of model might be mistaken. The mining data in Rumania stock using neural network models for price prediction also can be seen in [6]. The neural network such as MLP (multilayer perceptron) is not only successful in classifying of electroencephalogram (EEG) [12,21] but also it has been used to predict the future price of stock code in financial field.…”