Genetic Algorithmic Trading & With Programming, Neural Networks or Particle Swarm Optimisation & Relative Strength Index (RSI) - IT Assignment Help

Assignment Task

Algorithmic Trading Assignment

The assignment for this topic is going to look at the problem of formulating and applying trading rules using one or more of the techniques covered in the course: Genetic Algorithms, Genetic Programming, Neural Networks, Particle Swarm Optimisation, or Differential Evolution (or others of your own choice but check with me first). The choice of technique is up to you, as is the exact form of the problem you choose - take some time to read the related work - but below are two possible options based on the approaches covered in the lecture:

• Price prediction-based trading. Build a model to predicting the price for the coming day. This can be based upon any information you like but could include various key factors from previous days such as opening price, closing price, high price, low price, volume, Relative Strength Index (RSI), Exponential Moving Average (EMA), etc, or just values from the previous days trading. On top of this prediction, you would then build a trading rule which would choose to buy/sell/hold based on the current and predicted values (for example).

• Optimizing the parameters for pre-existing trading rules. Various technical indicators such as RSI or MACD can be used to trigger buy/sell actions based (for example) on the value of RSI or the relative positions of the MACD and signal lines. However, these are based on standard fixed values (e.g. MACD is built on the 26, 12, and 9 day EMA values), so an option here is to use approaches such as GAs to find a better combination of parameter values.

These are just suggestions and you can investigate either of these or some other aspect of algorithmic trading of your own choice (but feel free to check with me first), but whatever strategy you choose must involve some element of automated trading - buying and selling of stocks.

More sophisticated trading rules will attract more marks, but my strong recommendation is to start with something simple, and if (and only if) everything is working well then build in more complexity. For instance, you might have built a NN to predict prices that uses some EMA values, and you could then extend this to improve the predictions by optimizing the EMA parameters (period or weights for example), or (and this is getting very ambitious!) your strategy could modify its performance over time and modify itself appropriately.

Key Components

With the above problems you will need to train a model of some sort (GA, GP, NN...) so will need some notion of fitness or performance. This is obviously problem-dependent but at some point will need to evaluate profit: for whichever trading rule you are developing you will need to iterate through the training data and calculate your earnings (through returns or sales) on some notional amount of investment (let's say £10,000) if your trading rule was to be invoked.

• You will also need to keep some data in reserve for ie. keep some unseen historical data in reserve on which to evaluate the profitability of your final rule.
• Also, as with forecasting and prediction, you will be working with time-series data, so the size of the window needs to be considered (this will depend upon the characteristics of the data you are using).

This IT Assignment has been solved by our IT Experts at My Uni Paper. Our Assignment Writing Experts are efficient to provide a fresh solution to this question. We are serving more than 10000+Students in Australia, UK & US by helping them to score HD in their academics. Our Experts are well trained to follow all marking rubrics & referencing style.

Be it a used or new solution, the quality of the work submitted by our assignment Experts remains unhampered. You may continue to expect the same or even better quality with the used and new assignment solution files respectively. There’s one thing to be noticed that you could choose one between the two and acquire an HD either way. You could choose a new assignment solution file to get yourself an exclusive, plagiarism (with free Turnitin file), expert quality assignment or order an old solution file that was considered worthy of the highest distinction.