Insights and research on different trading algorithms

Posts

TWAP Strategy

/in , , , , , , /by

Time-Weighted Average Price (TWAP) is another trading algorithm based on weighted average price and in compare to Volume-Weighted Average Price its calculations are even simplier. Also it’s one of the first execution algorithms and unlike most algorithms nowadays it’s passive execution algorithm that waits for proper market price to come, doesn’t chase it.

 

Calculations

 

As TWAP doesn’t bother about volume it’s extremely simple to obtain it. All it takes is to get Typical Price for every period bar using equation below and then calculate average of Typical Prices.

 

Typical Price = (Close+High+Low+Open)/4

 

Let’s just take a look at example results calculated on 1-minute interval intraday Morgan Stanley’s stock.

 

Time Close High Low Open Typical Price TWAP
09:30:00 38.90 38.96 38.90 38.96 38.93 38.930
09:31:00 38.94 38.97 38.86 38.92 38.92 38.926
09:32:00 38.91 38.96 38.91 38.94 38.93 38.928
09:33:00 38.89 38.94 38.88 38.92 38.91 38.922
09:34:00 38.90 38.94 38.90 38.90 38.91 38.920
09:35:00 38.97 38.97 38.90 38.90 38.93 38.922
09:36:00 38.92 38.96 38.92 38.96 38.94 38.925
09:37:00 38.90 38.93 38.86 38.93 38.91 38.922
09:38:00 38.90 38.92 38.89 38.89 38.90 38.920
09:39:00 38.92 38.92 38.88 38.91 38.91 38.918
09:40:00 38.90 38.92 38.88 38.91 38.90 38.917
09:41:00 38.84 38.89 38.82 38.89 38.86 38.912
09:42:00 38.87 38.87 38.84 38.84 38.86 38.908
09:43:00 38.85 38.89 38.84 38.89 38.87 38.905
09:44:00 38.81 38.85 38.80 38.85 38.83 38.900
09:45:00 38.69 38.80 38.67 38.80 38.74 38.890

 

Strategy

 

The most common use of TWAP is for distributing big orders throughout the trading day. For example let’s say you want to buy 100,000 shares of Morgan Stanley. Putting one such a big order would vastly impact the market and the price most likely would start to raise. To prevent that, investor can define time period in TWAP Strategy over which they want to buy shares. It will slice evenly big order into smaller ones and execute them over defined period.

 

TWAP could be used as alternative to VWAP, but because of itssimplicity we have to remember about some pitfalls. Even if we slice big orders, we do it evenly, thus there is a possibility to hit on low liquidity period when our splitted order will impact the market hard. That’s why it’s recommended to use TWAP over short periods or on stocks that are believed to not have any volume profile to follow.

 

Be random

 

There is also another threat coming directly from dividing big order evenly, namely, other traders or predatory algorithms. Obviously trading in such a predictable way can lead to situation where other traders or algorithms would look through our strategy and start to “game” us.

 

Barry Johnson in his book suggests adding some randomness to the strategy as a solution to the issue. He says that “We can use the linear nature of the target completion profile to adopt a more flexible trading approach. At any given time, we can determine the target quantity the order should have achieve just by looking up the corresponding value on the completion rate chart.”

 

In practice it means that when we have run 4-hour TWAP we don’t slice the order into evenly parts, but otherwise we focus on percentage completion. So for instance we would want to have 25% of the strategy completed by first hour, 50% by second and 75% by third. That gives a more freedom into size of orders, so we can be more random with it and hence less predictable for other traders on the market.

 

TWAP vs VWAP

 

As both indicators use same mechanism, i.e. weighted average price, it’s common to compare them. Despite that VWAP’s nature is more complex and includes volume in its calculations, on  instruments with low turnover TWAP and VWAP values can be close. On the other hand when a session starts to be more volatile both indicators will diverge.

 

 

On a table below there are TWAP and VWAP calculated for whole trading day. As we can see at the beginning of the trading day the difference is less than a cent, but on close the difference raised up to 2 cents. It happened because during the day there were some small volume trades for lower price that didn’t affected VWAP, but did TWAP.

 

Time Close High Low Open TWAP VWAP
09:44:00 38.81 38.85 38.80 38.85 38.900 38.904
09:45:00 38.69 38.80 38.67 38.80 38.890 38.887
15:57:00 38.70 38.70 38.68 38.69 38.666 38.686
15:58:00 38.71 38.72 38.68 38.70 38.666 38.686

 

Summary

 

TWAP Strategy is another great tool for executing big orders without impacting the market too hard. Like everything it has its own pros and cons and it’s up to us to select if TWAP will be the best strategy to use for our case or maybe we should consider using VWAP or other strategy.

 

References

  1. H. Kent Baker, Greg Filbeck. “Portfolio Theory of Management” (2013) , pp.421
  2. Barry Johnson “Algorithmic & Trading DMA – An introduction to direct access trading strategies” (2010), pp. 123-126

 

 

Basics of High Frequency Trading

/in , , , , , , /by
Nanex’s High Frequency Trading Model (Sped Up)

Nanex released a video showing the results of half a second of worldwide high frequency trading with Johnson and Johnson stock. I simply sped up the footage to get a better feel of what it looked like. Blow Your Mind.

High frequency trading in action

CNN’s Maggie Lake gets a rare look inside the super-fast trading industry.

High Frequency Trading Explained (HFT)
Dave Fry, founder and publisher of ETF Digest, and Steve Hammer, founder of HFT Alert, discuss high frequency trading operations, fundamentals, the difference between algorithmic trading and high frequency trading, fluttering, latency and the role high frequency trading had in the May stock market flash crash in 2010.
 
TEDxNewWallStreet – Sean Gourley – High frequency trading and the new algorithmic ecosystem

Dr. Sean Gourley is the founder and CTO of Quid. He is a Physicist by training and has studied the mathematical patterns of war and terrorism. He is building tools to augment human intelligence.

Watch high-speed trading in action

Citadel Group, a high-frequency trading firm located in Chicago, trades more stocks each day than the floor of the NYSE.

Wild High Frequency Trading Algo Destroys eMini Futures

One of the scariest high frequency trading algos ran in the electronic S&P 500 futures (eMini) contract on January 14, 2008 starting at 2:01:11Eastern. During its 7 second reign, there were over 7,000 trades (52,000 contracts), and the price eventually oscillated within milliseconds, the equivalent of about 400 points in the Dow Jones Industrial Average!

HFT trading ideally must have the lowest possible info latency (time delays) and the maximum potential automation level. So participants prefer to trade in markets with high levels of integration and automation capacities in their trading platforms. These include NYSE NASDAQ, Direct Edge and BATS.
HFT is controlled by proprietary trading firms and spans across multiple securities, including equities, derivatives, index funds and ETFs, currencies and fixed income instruments.For HFT, participants want the following infrastructure in place:
– High speed computers, which need costly and regular hardware upgrades;
– Co-location.
– Real time data feeds, which must avert even the delay which could affect profits; and of a microsecond
– Computer algorithms, which are the heart of HFT and AT.

Benefits of HFT
– HFT is beneficial to traders, but does it help the total marketplace? Some market that is overall gains that HFT assistants cite contain:
– Bid-ask spreads have reduced due to HFT trading, making markets more efficient. Empiric evidence contains that after Canadian authorities in April 2012 imposed fees that deterred HFT, studies indicated that “the bid-ask spread rose by 9%,” possibly due to diminishing HFT trades. And thus facilitates the effects of market fragmentation.

– HFT assists in the price discovery and price formation process, as it is centered on a high number of orders (see related: How The Retail Investor Profits From High Frequency Trading.)

Basics of Machine Learning in Algorithmic Trading

/in , , , , /by

Algorithmic Game Theory and Practice, Michael Kearns, University of Pennsylvania,

Traditional financial markets have undergone rapid technological change due to increased automation and the introduction of new mechanisms. Such changes have brought with them challenging new problems in algorithmic trading, many of which invite a machine learning approach. I will briefly survey several algorithmic trading problems, focusing on their novel ML and strategic aspects, including limiting market impact, dealing with censored data, and incorporating risk considerations.

 

 

Machine learning for algorithmic trading w/ Bert Mouler

Harnessing the power of machine learning for money making algo strategies with Bert Mouler

Practical Tips For Algorithmic Trading (Using Machine Learning)
Evgeny Mozgunov from Caltech won an algorithmic trading competition hosted by Quantiacs. Jenia used machine learning tools to write his trading algorithm that now trades an initial $1M investment. He is talking about his approach and his main learnings. Jenia’s algorithm currently has a live Sharpe Ratio of 2.66.
 
Machine Learning and Pattern Recognition for Algorithmic Forex and Stock Trading
This is a whole course (20 videos) on machine learning and algorithmic trading. In this series, you will be taught how to apply machine learning and pattern recognition principles to the field of stocks and forex. This is especially useful for people interested in quantitative analysis and algo trading. Even if you are not, the series will still be of great use to anyone interested in learning about machine learning and automatic pattern recognition, through a hands-on tutorial series.
 

The following frontier of the technological arms race in finance is artificial intelligence. Improvements in AI research have triggered massive curiosity about the sector, where some consider a a trading, learning and thinking computer will make even today’s superfast, ultra-complicated investment algorithms appear archaic — and potentially leave human fund managers redundant. Could the next generation’s Buffett be a super-algo?

Some of the world’s largest cash managers are betting on it. AI investing may sound as, although fantastical sci-fi writer William Gibson said The future is already here, it’s simply not evenly dispersed.” Bridgewater, the world’s biggest hedge fund group, poached the head of IBM’s artificial intelligence unit Watson in 2012, and Two Sigma and last year BlackRock, another rapidly growing hedge fund that uses quantitative models, hired two former top Google engineers. Headhunters say computer scientists are now the hottest property in finance.

The quantitative investment world plays down the prospect of machines arguing that human genius still plays an important part, pointing out that the prospect of artificial intelligence that is complete is still distant, and supplanting human fund managers. But the confident swagger of the cash management nerds is unmistakable. There are quasi-AI trading strategies working their magic and the future belongs to them, they predict.

Artificial intelligence and video that is financePlay
The time will come that no human investment manager will manage to defeat the computer.” Or, as Agent Smith put it succinctly in The Matrix: “Never send a human to do a machine’s occupation.”

Yin Luo first learned to code after an used Apple II computer was brought back to China by his dad from a business trip to West Germany in 1985, when he was 11. But there were no games to purchase his home town in Heilongjiang province, in Yichun, so he made a crude variation of Tanks, where the player shoots down randomly created aeroplanes and taught himself to program.
It was arduous work. The computer’s lack of memory meant it crashed the program coding grew not too simple. He’d no floppy discs, so he learnt how to save the info on cassette tapes. “I just really needed something to play with,” Mr Luo recalls.

But the expertise paid off. Now, he is part of a growing tribe of brainiacs on Wall Street investigating the bleeding edge of computer science.

A network of 20 Linux servers is needed to run the hyper-sensible “ adaptive style turning” that was linear model, which is founded on a “machine learning” algorithm.

Machine learning is a branch of AI a diffuse term that is certainly frequently misused or misunderstood. While many people comprehend AI to mean sentient computers like the archvillains SkyNet in the Terminator films or HAL 9000 in 2001: A Space Odyssey, in practice everyday tools including Google’s language translation service, Netflix’s film recommendation engine or Apple’s Siri virtual assistant install basic forms of AI.

Quants have long used increasingly powerful computers to crunch numbers and uncover statistical signs of money-making opportunities, but machine learning goes a step further.

It can learn the difference between apples and bananas and sort out them, or perhaps instruct a computer how to play and quickly master a game like Super Mario from scratch. Machine learning can also be unleashed on “unstructured data”, such as for example jumbled amounts but also pictures and videos which can be typically not easy for a computer to comprehend.

More powerful computers mean that it are now able to be applied to financial markets, although the technique is old. “It’s a very bright area,” Mr Luo says. “Artificial intelligence is able to help you find designs an individual would never see. That may give you an enormous advantage.”

But that is not the only advantage of machine learning.

When marketplaces undergo what industry participants call a regime change that is “ ” and trusted strategies no more use, one of the classic challenges for quants is that their models can often prove worthless — or worse. Algorithmic trading strategies that print cash one day can blow the next up.

A machine learning algorithm adjusting to what works in markets that day, will autonomously develop and search for new patterns.
That means they can be used by asset managers as something to develop trade and strategies by itself, or perhaps to enhance their investment process, maybe by screening for patterns undetectable by people.

For Nick Granger, a fund manager at Man AHL, a quant hedge fund, that is the advantage that is critical. “You see it creating intuitive trading strategies in the bottom up, changing styles according to what works,” he says. “ We have been using machine learning for the past few years and have an interest in investing it in more.”

Nonetheless, machine learning has pitfalls. One of the largest challenges for quants is a phenomenon called “overfitting”, when an algorithm that is coded or exceedingly complicated finds false signals or specious correlations in the noise of data. For instance, a blog called “Spurious Correlations” notes that margarine consumption is linked to Nick Cage pictures to swimming pool drownings, and divorce rates in Maine.

When confronted by actual markets even if your model functions well in testing it can fail. Also, new data can be changed by the trading algorithm, says Osman Ali, a quant at Goldman Sachs’ asset management arm. “ you’re not affecting the weather, but if you deal marketplaces they are being affected by you If you crunch weather data.”

Nor can the most complex AI think as creatively as an individual, especially in a crisis. Brad Betts, a former Nasa computer scientist now working at BlackRock’s “ active equity” arm that is scientific, emphasizes the 2009 emergency plane landing on the Hudson river by Chesley Sullenberger of when machine is trumped by man as an example.

Truly, some quants remain sceptical that machine learning — AI or more broadly — is a holy grail for investment. Many see it just as a fresh, sophisticated gizmo to supplement their present toolkit, but others claim it truly is mainly a case of intelligent marketing rather than something genuinely ground-breaking.

They do’t constantly work, although “People are always desperate to find new ways to earn money in financial markets. He points out the human brain is uniquely adept at pattern recognition, “whether it really is love, a triangle or a face. Investment management is totally amenable to being addressed by computers designed to see patterns, but I’m not going to rush to use the latest hot algo to do so.”