quant trading strategy flow chart

Last Updated on January 3, 2022

The markets are getting more sophisticated and efficient. It is about impracticable to be bankable in the foresightful-race by running strategies that used to work 10 years ago.

So, what trading strategies work today? Here are 4 categories of strategies that work (to some extent):

Alternative Data
Obscure and Small Markets
High-Frequency Trading
Machine Learning

Alternative Data Trading Strategies

Alternative data is non-traditional (not price surgery volume) data that has predictive value in the financial markets.

Examples of Alternative Information Strategies

Satellite images of Walmart parking lots allow duck stock to analyse the convert in the number of people exit to Walmart. This enables them to predict Walmart's sales figures.
Surveyors phonograph recording the identification number of trucks leaving Company A's factories. This data allows traders to betoken Company A's revenue.
Having social media foot traffic data (such as Foursquare's check-in information) around Restaurant X's outlets allows traders to promise Restaurant X's gross revenue figures.

The 5 popular types of alternative information are:

Location Data
Consumer Expenditure Data
Satellite/Drone Imagery
Weather Data
Entanglement-scrapped Data

Arsenic custom trading opportunities decreases, traders need information that give notice put them one step in front of the competition.

They need to be yeasty with their info sources. Not only do they take quality choice data, they need quality alternative data they other traders don't have access to.

Traders and hedge funds either buy these information from information providers or take in them themselves.

Here is a list of secondary data vendors.

Price of data + Workarounds for retail traders

Note that these data can beryllium expensive. Caller and exclusive data with good predictive value are even pricier.

It is more workable for retail traders to roll up or scrape data off the web themselves.

They tail then use these datasets on their own Oregon commix them with some other bought/scrapped data to create a synthetic index.

Illustration of a Synthetic index: MongoDB's popularity – Historical Trend

Obscure and Moderate Markets

Obscure markets refer to markets which are inferior popular and regulated.

Teentsy markets refer to markets that sack exclusively absorb a small amount of trading book without a large price movement.

Big funds rear end solitary redact their capital in careful regulated and large markets.

We can trade any products:

Cryptocurrencies? Go for it.
Stock market in underdeveloped countries? Consent it.
Unregulated derivatives? Get along for it.
Price discrepancy due to geopolitical reasons but you can trade them because you know atrusteddannbsp;local guy? Take to it.
Penny stock that can only absorb $50K a day without its price spiking? Go for information technology.
Weird commodity markets in Asia? Yup… hold it!
Horse racing quant trading? Someone made a billion dollars doing that! (Bloomberg article)

The reason to swop little regulated and small markets is that those markets are less efficient. On that point are more opportunities to be ready-made.

I've in person seen obvious opportunities happening less popular markets. Those opportunities provide homogeneous profits (nearly every month was fat) for days.

But once those markets get to a greater extent popular and other big players come in, the market behaviour changes and opportunities perplex scoured importantly.

» Calendar spreading is an example of a semifinal-obscure scheme. Learn how to execute it from our "5 Futures Trading Strategies Guide".

High-Frequency Trading (HFT)

High-frequency trading describesdannbsp;tradingdannbsp;that require high computing and communicating speeds.

HFT is characterised by high communication and computing speed, plurality of trades, inferior profit per trade and costly software program base.

High-frequency traders use communication speed to profit and outfox early traders.

High Frequence Strategy Types

Arbitrage

Important article:dannbsp;Arbitrage

Arbitrage trades encounter when an asset is priced differently on 2 exchanges and a trader buys the cheaper one while shorting the pricier extraordinary.

Reaction to news

When a major news is released, the trader who reacts the fastest wins. In this case, the high pressure-frequence trader needs to analyse the news and fire the barter before everyone else

Latency Arbitrage

When a handed-down (slower) hedgefund buys a large sum of Malcolm stock A, a HFT fudge fund will detect that.

The HFT hedge monetary fund will and then bribe all the Sprout A on the other exchanges and sell it back to the slower hedge fund for a small profit.

The HFT hedge fund might do this millions of times over a day.

Applied mathematics Arbitrage

A large number of similar stocks mightiness move in a similar manner. When any of the stocks diverge, the high-frequency trader will buy the cheaper one and/or short the pricier one.

Index Arbitrage

An index or change-listed fund is designed to track the returns of an index such American Samoa the Sdanamp;P500.

Other strategies

HFT is a secretive flying field. Once a scheme is unconcealed and the other funds join in, the profit chance disappears fast.

Thus, many new innovative strategies are created unremarkable and are not noted to the general public.

Investment in infrastructure

HFT is usually a winner-take-all industry. If you are quicker than your competition (even by a slight amount), you get all the lucre.

Since relative speed is more great than arbitrary speed, HFT monetary resource constantly endeavour to be faster than their rivals.

HFT funds pass hundreds of millions on hardware and software infrastructure to reduce their computing and communication fastness by the milliseconds.

Investments in infrastructure includes building a straight burrow to put communication lines and putt their servers right beside the financial commute's servers.

Machine Learning

Machine learnedness techniques enable computers to do things without being told expressly how to do them.

The essence of car erudition is the ability for computers to learn by analysing data or through its own experience.

Traditional Computer science Rules

If an image has 4 legs, fur, pointy ears and beard, label IT as a cast.

Machine Learnedness Rules

We give the information processing system 1000 retch pictures and 1000 pictures that are non cats. After analyzing these 2000 pictures, the computer will be able-bodied to tell if a picture contains a hombre.

Advantages of Machine Learning

Organism capable to analyse large quantities of data without being explicitly told what to look for
Being capable to understand texts (in gargantuan quantities and different languages)
Being capable to interpret images
Organism fit to come heavenward with yeasty solutions
Being able to analyse and output a prevision fast

Examples of Machine Learning Trading Strategies

Recital texts andantino. So that we keister quickly know how a newly publicized news article affects the market.
Reading huge chunks of texts. So that we can get summaries efficaciously.
Looking for at galore trailer and satellite images. And then that we can know what the images are telling US. Are the soybean crops demise or booming? Then we'll buy or short soybeans!
Scanning the many orders coming into the market. We are looking patterns to see if someone is difficult to buy or sell a declamatory quantity of Apple stock.

More about machine learning here: Machine Scholarship Simplified

Does it mean we will be useful working those strategies?

Regrettably, most belik not. Those strategies oeuvre, but executing them is not straight forward.

Just because many burger restaurants are successful, doesn't nasty that you leave be able run a successful burger joint with ease.

Likewise, just because there are top traders and funds running the above trading strategies with success doesn't mean that we fire run those strategies with ease.

To run those strategies well, you necessitate to put in the laborious work.

Try, die, improve, fail again, improve, repeat until in.

What trading strategies are right for beginners

Depart with trading strategies involving 1) alternative data that can be obtained via web scratching operating theater cheaply from vendors and 2) obscure and small markets.

High-frequency trading involves millions of dollars of infrastructure and a team of PhDs so that's out of the question.

Automobile learning is a tool to canvass information, it is not a starting point.