An Intelligent Hybrid System for Forecasting Stock and Forex Trading Signals using Optimized Recurrent FLANN and Case-Based Reasoning

Abstract

A precise prediction of future market trends is inevitable for traders in stock and foreign exchange market. However, it is a challenging task to have a profound understanding of technical indicators, including market-dominant factors and inherent process mechanism. In order to expedite the trading decision-making process, an intelligent stock trading system is proposed blending dynamic time windows coupled with case-based reasoning (CBR), and recurrent function link artificial neural network (FLANN) optimized with firefly algorithm. The idea of using CBR module is to offer a dynamic window search to assist the recurrent FLANN architecture for superior fine-tuning the trading operations. This integrated stock trading system is intended to pick the buy/sell window of target stock to maximize the profit. To demonstrate the applicability of the projected system, the time-series data from IBM, Oracle stock data, and in currency Euro to INR and USD to INR exchange data on daily closing stock prices are used for simulation. The assessment of performance of the proposed model is realized using error measures such as mean absolute error and mean absolute percent error. Furthermore, the experimental results obtained with and without using CBR has been exhibited for different stock and forex trading.

Analisis Peramalan (Forecasting) Penjualan Dengan Metode ARIMA (Autoregressive Integrated Moving Average) Pada Huebee Indonesia

“…Penelitian ketiga membahas tentang Sinyal Trading Forex menggunakan Optimized Recurrent FLANN. Hasil dari penelitian yang dilakukan bahwa metode peramalan terbaik untuk peramalan tren pasar saham dan RFLANN Forex memiliki nilai MAPE paling kecil yaitu 5,37% dibandingkan metode lainnya [6]. Penelitian keempat dilakukan membahas tentang data perdagangan Yahoo Finance.…”

Effectiveness of the Relative Strength Index Signals in Timing the Cryptocurrency Market

“…The recent studies also show the potential of using TA in fully developed economies [ 22 ]. Recently, the popular approach has been to pre-act prices using neural networks and methods traditionally used in predictions and simulations, combining forecasting and TA [ 23 , 24 , 25 ]. The authors note that combining both methods can be successful and will be the subject of further research by the authors.…”