NARX - Next Day Prediction of Stock Prices

Hi,

I am using a Time Dalay NARX Neural Network to predict the next day prices of stocks from a particular industry sector (marine and offshore, Singapore Exchange). I am using the attached dataset along with the following code for the prediction attempt. The prediction results are quite bad.

I had read that autocorelation and cross-correlation is required to get the number of delays, but I have been unsuccessful in implementing it. Could you modify the code below to implement auto-correlation and cross-correlation for getting the appropriate delays? It would be great if you have any suggestions to improve prediction accuracy. (Using additional data, different training algorithm, using additional algorithms etc.)

    data=csvread('keppelcorp.csv',1,1);
    inputSeries = tonndata(data(2:end,:),false,false);
    targetSeries = tonndata(data(1,:),false,false);

    input = data(1:end,2:end);
    target = data(1:end,1);
    N=int32(0.7*size(input,1));  % how much data to use for training
    inputSeries = tonndata(input(1:N,:),false,false);
    targetSeries = tonndata(target(1:N,:),false,false);

    inputSeriesVal = tonndata(input((N+1):end,:),false,false);
    targetSeriesVal = tonndata(target((N+1):end,:),false,false);

    inputDelays = 1:10;
    feedbackDelays = 1:10;
    hiddenLayerSize = 20;
    net = narxnet(inputDelays,feedbackDelays,hiddenLayerSize);

    [inputs,inputStates,layerStates,targets] = preparets(net,inputSeries,{},targetSeries);
    net.divideFcn = 'divideblock';  % Divide data in blocks
    net.divideMode = 'time';  % Divide up every value
    net.trainFcn = 'trainlm';  % Levenberg-Marquardt

    % Train the Network
    [net,tr] = train(net,inputs,targets,inputStates,layerStates);
    plotperform(tr)

    Y = net(inputs,inputStates,layerStates); 

     % Prediction Attempt
    N=size(inputSeriesVal,2);
    delay=length(inputDelays); 
    inputSeriesPred  = [inputSeries(end-delay+1:end),inputSeriesVal];
    targetSeriesPred = [targetSeries(end-delay+1:end), con2seq(nan(1,N))];
    netc = closeloop(net);
    [Xs,Xi,Ai,Ts] = preparets(netc,inputSeriesPred,{},targetSeriesPred);
    yPred = netc(Xs,Xi,Ai);
    perf = perform(net,yPred,targetSeriesVal);

    perf_mae = mae(net,targetSeriesVal, yPred);
    perf_mse = mse(net,targetSeriesVal, yPred);

    close all;
    targetSeriesVal = targetSeriesVal(2:end);
    targetSeriesVal(end+1) = targetSeriesVal(end);
    figure;
    plot([cell2mat(targetSeries),nan(1,N);
          nan(1,length(targetSeries)),cell2mat(yPred);
          nan(1,length(targetSeries)),cell2mat(targetSeriesVal)]')
    legend('Original Targets','Network Predictions','Expected Outputs')

    figure;
    plot([cell2mat(yPred);cell2mat(targetSeriesVal)]')
    legend('Network Predictions','Expected Outputs')

    disp('Performance is')
    perf

    disp('Mean absolute error performance is')
    perf_mae

    disp('Normmalized MSE Performance is')
    perf_mse

    disp('Next day closing price was forecasted to')
    yPred(end)

    csvwrite('Real 1st column and 2nd column Predicted Prices.csv',[targetSeriesVal',yPred']);

Answer 1

[Greg Heath]

> I am using a Time Dalay NARX Neural Network to predict the next day prices of stocks from a

> particular industry sector (marine and offshore, Singapore Exchange). I am using the attached

> dataset along with the% following code for the prediction attempt. The prediction results are

> quite bad. I had read that autocorelation and cross-correlation is required to get the number

> of delays, but I have been unsuccessful in implementing it. Could you modify the code below

> to implement auto-correlation and cross-correlation for getting the appropriate delays?

I'm surprised to hear that. If you just search in the NEWSGROUP and ANSWERS using

greg NNCORR

NEWSGROUP 11 hits

ANSWERS 53 hits

> It would be great if you have any suggestions to improve prediction accuracy. (Using

> additional data, different training algorithm, using additional algorithms etc.)

My answer is simple:

Take a look at some of my posts.

Hope this helps.

Thank you for formally accepting my answer

Greg