Week 10 Update

Writing up the chapter 3 of my treatise and stringing together all the different parts.

Mid Semester Break

did svm machine learning classification of liquidity rise or fall in the next period based on information about liquidity and algorithmic trading frequency in the past periods. The results are inconclusive as yet. Also I did research on the Kaplan Meier Estimator and its relevance to the dark pool problem.

Week 9 Update

Finished off the dark pool simulations and granger causality testing results. However needed to redo the granger causality results in order to account for endogeneity problems. First thought was to do generalized method of moments however Sanjay prefered machine learning techniques as these were less archaic.

Week 6 and 7 Semester 2

conducted dark pool simulations to find the optimal algorithm for dark pool allocations. This was done on Matlab

Week 5 Semester 2

This week I met with Sanjay and he suggested adding a norm squared term to the Liquidity Algorithmic-Trading Frequency regression model to reduce the overfitting in the model.

Also, he asked me to start conducting the dark pool simulation. In the dark pool simulation I will be simulating dark pools using a Poisson Distribution and I will have a Person class that will conduct a multi armed bandit algorithm in order to optimize allocation across dark pools in the minimal time.

Week 4, Semester 2

This week I finished up the Granger Causality Tests on the 20 stocks from the ASX. Unfortunately we could not conclude that the proportion of algorithmic traders granger causes liquidity changes.

Also, I finished writing up the chapter on Cointegration, Granger Causality and Spurious Regression.

Now I will just show the results to Sanjay and then move on to conducting dark pool simulation experiments.

Week 2, Semester 2

Currently I am writing the chapter on cointegration, granger causality test and spurious regression.

Also, I am doing experiments on stocks to test for causation relationship between algorithmic trading frequency and liquidity.

Week Starting 18.07.2011

Achievements for this week:

Experimented to verify the hypothesis that Algorithmic Trading affects liquidity positively. That is when Algorithmic Trading Frequency rises Liquidity rises and when Algorithmic Trading Frequency  falls so does Liquidity.

• Extracted records regarding the trades of 20 stocks for the three year duration of the data available.
• Used MATLAB to measure the algorithmic trading frequency of these stocks on randomly chosen days for 5 minute blocks. Plotted the results on a line graph.
• Used MATLAB to measure the bid ask spread of these stocks on the same days. Plotted the results on a line graph. The bid ask spread is an indicator of liquidity.
•  It was observed that there is a correlation between algorithmic trading falls so does liquidity and this seems to indicate that there is a possibility that algorithmic trading may cause it. However causation does not equal correlation and so the Granger Causality Test was used on R to verify causality. Preliminary tests indicate causality does exist. However further verification is required.

Week Starting Monday, 11 July 2011

Focus for this week: To replicate the experimental analysis from the paper 'Does Algorithmic Trading Improve Liquidity?' By Hendershott et al.

Achievements for Monday:
1. Made  the plan for how to replicate the experiment from the above paper.
The most important steps are as follows:
(i) Find the number of stocks and group them into quintiles by market capitalization.
(ii)  By quintiles, graph the number of algorithmic traders involved across the time period for which data is available.
(iii) By quintiles, graph quoted half spreads, quoted depth, and effective spread.
(iv) Perform the regression analysis of algorithmic trading on liquidity.
(v) Identify whether there is an effect on frequency of AT due to liquidity.
(vi) Find Instrument Variable.
2. Towards achieving the plan above, I have done the following on Monday: Wrote up and started executing the python scripts to list and count the number of stocks, the dates for which the data exists, and the mean market capitalization for each stock. These all allow me to progress towards achieving step (i). I also sent an email to my finance supervisor Andrew Lepone regarding the question of what instrument variable we may use in the context of ASX. Since the paper focuses on the NYSE and over there they used the introduction of the autoquote as the instrument variable-and we cant do that here.


Achievements for Tuesday
Today I wrote up and executed the python scripts to extract the top market cap quintile stocks' trades. It took a very long time because of the size of the data that I was working with and the inefficiency of my scripts-which I didn't detect and correct till Thursday.
Achievements for Wednesday
Same as on Tuesday.
Achievements for Thursday
Corrected the inefficiencies in my python script so that it finished in 2 hours rather than the estimated 30 days. Also, started counting the average number of algorithmic trades as a percentage of all trades every 5 minutes, on a monthly basis for the period 31 Oct 2006 to 26 Oct 2009. This is only for the top quintile stocks.

Week: 20-24th June 2011 (Semester 1: EXAM WEEK 2)

This week my goal is to see if I can analyse the data provided to me by Andrew Lepone and gain some useful insight into Algorithmic Trading in the ASX.


On Thursday:

I wrote a script on Matlab to analyse a weeks worth of Data pertaining to the stock with the symbol AAC.

What I was trying to do was discover the number of algorithms that were involved in the trading of stocks every 5 minutes from the beginning to the end of the trading day for the entire week of 30 Oct 2006 and 3 Nov 2006.

I graphed the results and found a peak in algorithmic trading at the beginning and in the middle of the day.

On Friday:

I am trying to analyse all other stocks for the same week in the same way as I analysed AAC, to see if AAC follows the norm or whether it is different.

Week 13 Update

Gave Sanjay Chawla a first draft of my literature review to read over.

week 12 Update

Working on literature review as well as trying to download the data to a server where there is enough space to fit it. This is problematic since the data is 55GB-which is quite big.

Got a hard drive for storing the 55GB of data and started performing MATLAB experiments on it.

Had trouble opening the csv file containing the data at the beginning, however, after much surfing of the net, I found a csv file splitter at this URL: http://www.fxfisherman.com/forums/forex-metatrader/tools-utilities/75-csv-splitter-divide-large-csv-files.html#post727.

This split the csv file into over 7000 csv files which were easier to open.

Week 11 Update

Acquired data from Andrew Lepone to conduct data mining experiments on from the ASX for the last 3 years, minute by minute

Week 10 Update

Working on my literature review, and project progress report.

Week 9

I am reading the following article:

"Optimal Allocation Stratergies for The Dark Pool Problem"by Agarwal et al. and preparing my literature review for Week 13.

Week 8 & Mid Sem Break Update

For these two weeks I was just finding and reading more articles, some of which are useful  some of which are not-although they provide general background knowledge for my thesis.

This is in preparation for the literature review due in week 13.

It was hard these last few weeks because my external supervisors went on work related international travels so there was no one to guide me or explain things to me where i was lost-was pretty much making my own way.

Will talk to Sanjay when he gets back in week 9 though.

Week 7 Update

Met with an investment bank employee who suggested that the Flash Crash and the effect of Algorithmic Trading on Volatility was not as interesting a topic as the effect of Algorithmic Trading on Liquidity. She stated that she had come across evidence that Algorithmic Trading reduced liquidity. Which I contrasted to the 'Does Algorithmic Trading improve Liquidity?' paper by Hendershott.

Week 6 Update

Met with an investment bank employee and discussed the possibility of doing my research thesis on the effect of  algorithmic trading on market volatility. He stressed the Flash Market Crash as a good example of how algorithmic trading is bad for market volatility. I thought the paper regarding Algorithmic Trading and Information written by Hendershott provided a good contrast with this and presented an opportunity to explore further.

Wrote up my research thesis proposal based on this.

Week 5 Update

This week I attended the meeting with an investment bank employee regarding Algorithmic Trading. It turned out the content of the meeting was insufficient for my purposes and further meetings were organized.

Sanjay Chawla gave me the following book to read "Empirical Market Microstructure: The institutions, economics, econometrics of securities trading" by Joel Hasbrouck.

I started to write up my project proposal.

Week 4 Update

This week I studied the paper "Algorithmic Trading and Information" by Hendershott et al. It addressed the question that Andrew asked me to consider very well. That is how can we study and exploit the relationship between the market and algorithmic trading.

The research was done based on the data collected from the top stocks on the Deutsche Market. It conjectured and proved that Algorithmic Trading improves liquidity, has no impact on volatility, can be detected through fee reductions, has a more significant impact on human trading than vice versa and also that it is more close to the efficient price than human trading more often.

The paper used vector auto regressions, impulse functions and covariance matrices in its methodology to understand the relationship between the stock market and algorithmic trading.

Week 3 Update

I organised regular Weekly meetings with my supervisors on Thursdays 5-6pm.

This week my supervisors encouraged me to read material by Hendershott as he is the best expert in Algorithmic Trading.

Also, we discussed the idea of trying to identify rules for algorithms that instigated responses in the market for the topic of my thesis. For example, predicting the volatility of the market based on how an algorithm is behaving at the moment. According to Andrew this is a major point of interest in Finance these days.

I also read the book "Option Theory with Stochastic Analysis" in order to learn about how to analyse data. This topic brought up the concept of Brownian Motion, Inverse Gaussian Aggregation and Logarithmic Returns to stocks.

Week 2 Update

 I have studied the article "Algorithmic Trading Strategy Optimization Based on Mutual Information Entropy Based Clustering" in depth and presented it at the research group meetings that Sanjay Chawla holds weekly for all of his research students.

I had to teach myself Information Theory in order to understand this article.

I found many mathematical errors as well as a lack of explanation for why the authors did certain things. As a consequence, my supervisors and I dismissed it as a Tier C article with too many flaws to be taken seriously.

However, I still consider it to have been a good learning experience as it taught me how to understand an academic article.

I read these two resources to help me out in how to read an academic article:

"Evaluating Research Articles From Start to Finish" by Ellen R. Girden
"The Research Student's Guide to Success" by Pat Cryer.

At this stage I have still not decided what my question is going to be in my thesis and am still reading articles to understand what the area of algorithmic trading is all about.

Here are some other articles that I have studied, though not in as much depth as the one mentioned above:
"Data Stream Mining For Market Neutral Algorithmic Trading"
"Efficient Trade Execution Using A Genetic Algorithm in an Order Book Based Artificial Market"
"Efficient Event Processing through Reconfigurable Hardware for Algorithmic Trading"

I also organized an interview with an undisclosed financial institution's algorithmic trading team member to discuss how they use algorithmic trading and how they will be able to help me in my research thesis-Contact me for more information if interested.

Week 1 Update

Hello! This is my first blog for my ELEC 4712 Research thesis.

It is already Week 1  of Semester 1, 2011 and I spent my first week and holidays reading the following articles:

Chaboud, A. , Chiquoine, B. , Hjalmarsson, E., and Vega, C., 2009, Rise of the Machines: Algorithmic Trading in the Foreign Exchange Market, International Finance Discussion Papers: Board of Governors of the Federal Reserve System Number 980, 1-46


Hendershott, T., Jones, C.M., and  Menkveld, A.J., Does Algorithmic Trading Improve Liquidity?

Gsell, M., Assessing the impact of algorithmic trading on markets: a simulation approach.

Domowitz, I.,  and Yegerman, H., 2005, The cost of algorithmic trading: A first look at comparative performance

I have also attended preliminary informal meetings with Sanjay Chawla and Andrew Lepone to ask them about being my joint supervisor and they have agreed. However, I will be getting their signatures on Wednesday and Thursday respectively so that I can hand in my topic registration form. Have already got Rafa Calvo as my SEIE supervisor.