A Feasible Idea-Proposal for an Algorithmic Trading App supplemented with Deep Learning features.

Algorithmic Trading is a method of executing orders using automated pre-programmed trading instructions accounting for variables such as time, price, and volume to send small slices of the order (child orders) out to the market over time.
This concept and practice of Algorithmic Trading has been evolving over the past few years, and is now a continuous evolution on its own.

By now, there are a host of Algorithmic Trading Tools & Software in the global market. Even Algorithmic Trading Apps have started evolving, as expected. Few useful links are provided below.
9 great tools for Algorithmic Trading
An Algorithmic Trading App from Trade Smart
STREAK - An Algorithmic Trading App from Apple

After navigating through the above links, one might still wonder on how many of these tools, software, and apps are actually equipped with Deep Learning features. 
It is very much possible and obviously true that continuous research and development is in progress, in order to achieve the extra mile in Algorithmic Trading with Deep Learning.

Deep Learning methods are prophesied to revolutionize the field of AI and represents a step towards building autonomous systems. We live in an era where we are creating unbelievable amount of data everyday. Neural networks hold the ability to scale problems that were previously unsolvable, causing a huge wave of interest in this field.

One of the primary goals of the field of artificial intelligence (AI) is to produce fully autonomous agents that interact with their environments to learn optimal behaviors, possibly improving over time through trial and error.
Currently, deep learning is enabling many other machine learning algorithms, for example reinforcement learning to scale to problems that were previously intractable, such as learning to play video games directly from pixels. Deep Learning has penetrated a lot of fields, including finance. However its reach in high frequency trading is limited, specifically due to the computational constraints and primitive problem modeling methods.
There has been a lot of other machine learning algorithm tried and tested in the field of high frequency trading. There has been a lot of work done specifically in terms of feature engineering in High Frequency Trading, focused on simpler models like linear regression, multiple Kernel learning, maximum margin, traditional model-based reinforcement learning etc.
However, due to the computational complexity of Deep Learning models, lesser work has been done in terms of incorporating such recent and more complex models and instead more focus is made towards extracting useful features from the current trading book state and recent trading behavior.
The common feature values like bid-ask spread, percentage change in price, weighted price etc. and some specialized features like order imbalance are among many others that can used in our proposed model.

We aim to create a Pipeline which uses information about the past trading behavior and current snapshot of the order book to predict price movement in the near future. We will then aim to use this information for making decision in the market for maximum profitability.

Complete Pipeline 
(Refer to above block diagram for a better understanding of flow of the Pipeline)

The complete pipeline will be broadly divided into three sections :

1. Pre-Training - The model needs to be trained beforehand using the data available from the market activity of previous days. The trained weights are saved and used to initialize the model before taking it live.
2. Prediction - Features are created on the run and the model predicts price movement of the stocks using these features at every tick. Bid and Ask orders are placed in or withdrawn from the market using this information.
3. Online Training - Running parallel to the predictions, we need to accumulate the feature values and corresponding ground truth values which we will get in the near future. Once a mini-batch is formed, the weights are updated by tuning the model using this batch and the same process of accumulating data starts again.

This is just a brief note on just one of the many module features in the Deep Learning supplement that can be injected in an Algorithmic Trading model.
The ability to give precise and fast prediction for the price movement of stocks is the key to profitability in High Frequency Trading. Deep Learning methods can have a lot of potential in the field of High Frequency Trading. 
Once modeled, we need to further analyze the model’s performance based on it’s prediction accuracy as well as prediction speed across full-day trading simulations.