Take the 2-minute tour ×
Quantitative Finance Stack Exchange is a question and answer site for finance professionals and academics. It's 100% free, no registration required.

I have recently undertaken a research into automated algorithmic trading algorithms.

The aim of the research is to focus on studying algorithmic trading and trying to improve a basic implementation of an algorithm that exists.

The algorithms usually analyze past market data, social media events and other factors in near real time to find patterns and trends using an auto-regressive learning model with gradient descent and thus they attempt to predict market movements.

I am currently reading through the book "Algorithmic trading and DMA by Barry Johnson" as this was suggested in one of the forums that I encountered.

I realize that there are various models that have been implemented. Given the time frame for the project, which is 8 months, I would like to know if there are any good suggestions on starting points for this project.

For example, any books, papers that you can recommend.

More specifically, it would be helpful if you could suggest a specific algorithm that I can look at to start with considering I am new to the field of algorithmic trading in particular.

Since, the question appears vague, I have added a description of the project below http://algorithmic-trading-research.tumblr.com/post/12885213702/project-description

share|improve this question
1  
This question is way too basic to be allowed here. –  chrisaycock Nov 17 '11 at 21:53
    
@chrisaycock - Sorry about that, can you redirect me to a more appropriate source of information ? –  k9ty Nov 18 '11 at 4:48
1  
For a master's thesis, your best bet is to ask your supervisor. –  chrisaycock Nov 18 '11 at 4:51
add comment

migrated from money.stackexchange.com Nov 16 '11 at 0:03

This question came from our site for people who want to be financially literate.

closed as off topic by Ryogi, Steve, Joshua Ulrich, chrisaycock Nov 17 '11 at 21:52

Questions on Quantitative Finance Stack Exchange are expected to relate to quantitative finance within the scope defined by the community. Consider editing the question or leaving comments for improvement if you believe the question can be reworded to fit within the scope. Read more about reopening questions here.If this question can be reworded to fit the rules in the help center, please edit the question.

2 Answers

Your question is very vague, which makes it almost off-topic.

I would suggest you to look into trend-following algorithms, as the most basic ones are very easy to understand; look for trading strategies involving moving averages.

However, if you want to improve an algorithm within 8 months, alone, I think it will be pretty difficult.

What is that for?

My educated guess: a master thesis.

If that's the case I'd suggest you to look to apply the trend-following strategies on different markets and see if they work everywhere (they don't) and explain why.

Algorithmic trading is not easy, it requires a lot of work, a good infrastructure and depending on the data required, a large amount of money.

share|improve this answer
    
Yeah, it is for a master thesis. I did not know how to better frame the question but I have put up a project description algorithmic-trading-research.tumblr.com/post/12885213702/…. Hopefully it makes more sense. I will look into trend-following strategies and how they work on different markets. –  k9ty Nov 16 '11 at 17:06
    
I disagree with this answer: trend following is not "algorithmic trading". It is systematic, but algorithmic trading has a specific meaning related to order execution. –  Shane Nov 17 '11 at 2:23
    
@Shane: thanks for the comment and answer, I actually did not know that algo-trading was specifically used for execution strategies. The wikipedia article seems to think otherwise, maybe a citation could be interesting. Anyway, I thought k9ty was meaning systematic trading more than algorithmic (using your terminology). –  SRKX Nov 17 '11 at 8:48
add comment

The term "algorithmic trading", as its most often used, refers to strategies that are used to optimally execute an existing view (this usually means trying to reduce market impact). The most well-known benchmark strategy is VWAP, which targets the "volume weighted average price" (similar to TWAP, which instead tries to evenly space trades over time). Other examples include things like Iceberg, Sniper, and Guerrilla.

This is a very big area of study. The book you cite is a good source; I also really like "Optimal Trading Strategies". The classic paper on the subject is "Optimal Execution of Portfolio Transactions" (Almgren and Chriss 2000).

share|improve this answer
    
Thanks Shane, very helpful info. –  k9ty Nov 17 '11 at 4:29
3  
I disagree with your definition of algorithmic trading, though I know it is used by more people in this form. Algorithmic trading means you let an algorithm--unmabiguous step-by-step rules--dictate your trading. There is no gut feeling or other BS involved because it is ambiguous. In fact you do not even need computers to engage in algorithmic trading... You can calculate everything on paper. Computers make it easier and faster though. –  Dmitrii I. Nov 22 '11 at 12:42
add comment

Not the answer you're looking for? Browse other questions tagged or ask your own question.