Abstract:
Foreign currency exchange plays an important role for currency trading in the financial market.
Modern approach to the foreign currency exchange market requires support from the computer
algorithms to manage huge volume of transactions. There occurs problems like trading without a
plan, failing to adapt to the market, having unrealistic expectation and many more. Due to these
problems, predictions are to be done. This paper investigates on prediction of foreign exchange
market using neural network and sentiment analysis. There are many algorithms for performing
prediction but different algorithms have different accuracy. One of the best method with high
accuracy is given by Artificial Neural Networks (ANN). Neural network parameters include
number of hidden layers, number of neurons, use of bias neurons, activation functions and training methods. Input nodes are price of gold, crude oil, Nasdaq index, yesterday’s price. Our model contains 4 input node, 1 hidden layer and 7 hidden nodes. At first, pre-processing is done and inputs are fed to the neural network. By using backpropagation algorithm, training is done and then testing is performed. Mean absolute percentage error is found to be 0.39%. The price
movement is also directly related to market sentiment. We aim to employ a statistical technique to the opinion of different traders and finding the overall sentiment. Sentiments are taken from tweets and then filtering the tweets are performed. After that, features are extracted and by using Naïve Bayes algorithm, the results are classified as positive or negative.
