Deep Learning in Finance

Sonam Srivastava | Oct. 1, 2017

I am writing this post as a follow up on a talk by the same name given at Re-work Deep Learning Summit, Singapore. In the talk I tried to detail the reasons why the financial models fail and how deep learning can bridge the gap. Further on, I moved on to present three use cases for deep learning in Finance and evidence of the superiority of these models .

Financial Models

While finance is the most computationally intensive field that there is, the widely used models in finance — the supervised and unsupervised models, the state based models, the  econometric models  or even the stochastic  models  are marred by the problems of over fitting, heuristics and poor out of sample results.  Which is because,   the financial domain is hugely complex and non-linear with a plethora of factors influencing each other .

To solve this, if we look at the research done in Deep Learning in proven fields of image recognition, speech  recognition  or sentiment analysis we see that these models are capable of learning from large scaled  unlabelled data, forming non-linear relationships, forming recurrent structures and can be easily tweaked to avoid over-fitting.

If these models find application in the discipline of finance then the applications are far and wide. These models can be used in pricing, portfolio construction, risk management and even high frequency trading to name a few fields . So let us tackle a few of these problems.

Return Prediction

Taking the sample problem of predicting daily Gold Prices,  we first look at the traditional methods.


Using the  Autoregressive Integrated moving Average model,  which tries to predict a stationary time series keeping the seasonal  component in place  we get a result

ARIMA Results


If we add related predictor variables to our auto-regressive model and move to a  Vector Auto Regressive mode l, we get these results —

VAR Results
VAR Result 1

Deep Regression

Using the same inputs if I fit a simple deep regression model on the data, I get far better results,

Deep Regression Result
Deep Regression Data

Convolutional Neural Networks

Modifying my architecture to use convolutional neural networks  for the same problem, my  results   are

CNN Result
convolutional neural networks Data

These results are drastically better. But the best results come next.

Long Short Term Memory (LSTM)

There you go! Using these variations of recurrent neural networks, my results are:

LSTM Result
Mean Squared Error

So overall  the trend of the mean squared errors is a revelation !

Mean Squared Errors

Portfolio Construction

The second financial problem we will try to tackle using deep learning is of portfolio construction. The application of deep learning to this problem has a beautiful construct. My study is inspired by a paper titled Deep Portfolios.

What the authors of the paper  try to do is  to construct  auto-encoders  that map a time series to itself.   The errors of prediction using these auto-encoders becomes a  proxy of a stock beta  (correlation to the market), the auto-encoder being a model of the market!

Ch oosing   a diverse set of stocks based on above mentioned auto-encoder errors, we can construct a deep index using another deep neural network and the res ults are quite good.

Deep Index Result

The deep neural network here has become a index construction method that replicated the index using the   stocks.

But that’s just the beginning of it! If we apply smart indexing, where I remove periods of extreme drawdown from the index and train my index mapping deep neural network on the smart index, I am able to outperform the index in a drastic way!

Smart Portfolio Result

This technique has a huge potential in the field of portfolio construction!


The current trends in the financial industry are leading the way to more sophisticated and sound models finding their way in. Technology is a huge area of stress for all the banks with a large number of data scientists entering the field. You have hedge funds like  RelTec  and  Worldquant  that already  use  this technology in their trading. With the superior results shown by these sophisticated models in other fields and the huge gaps open in the field of financial modelling, there is a scope of dramatic innovations!

Better solutions to our critical problems in the field of finance and trading would lead to increased efficiency, more transparency, tighter risk management and new innovations.

PS: The code used for all the  above  analysis can be found on my  github repo

I’m planning my next post on deep RL for portfolio management, so keep tuned in!

Any good suggestions are welcome.

Please visit my website /to know more about the investment strategies I manage!

Drop in your email to continue reading

Leave a comment

Welcome to Wright!

We are dedicated to help you invest better using our superior research backed portfolios.

Drop in your email to stay in touch!

© Copyright Wryght Research & Capital Pvt Ltd All Rights Reserved