=Paper=
{{Paper
|id=Vol-1968/abstract
|storemode=property
|title=None
|pdfUrl=https://ceur-ws.org/Vol-1968/abstract.pdf
|volume=Vol-1968
}}
==None==
<pdf width="1500px">https://ceur-ws.org/Vol-1968/abstract.pdf</pdf>
<pre>
Empirical Evaluation of Neural Networks on
   Stocks of Pakistan Stock Exchange

          Ali Abdullah, Ambreen Hanif, and Noman Javed

                  Namal College Mianwali, Pakistan
      aabdullah2013@namal.edu.pk, ambreen.hanif@namal.edu.pk,
                    noman.javed@namal.edu.pk



 Abstract. Stock market attracts many investors to earn money by in-
 vesting timely. But stocks are very volatile and their non-linear behavior
 make them more unpredictable and it is humanly impossible to pre-
 dict the stocks accurately. Neural networks based machine learning tech-
 niques can be employed for the said purpose. Since there are many types
 of neural networks available, to find the suitable type and architecture
 of the network, problem specific empirical evaluation is required. This
 work focuses on assessing different types of neural networks for predict-
 ing stocks of Pakistan Stock Exchange. Recurrent neural networks are
 found to outperform other networks on all the evaluated stocks.

 Keywords: Pakistan Stock Exchange, Feedforward Neural Network,
 Recurrent Neural Network, Deep Learning

</pre>