15

Windham Capital Management is using hidden markov models for their Risk Regime Strategies. Mark Kritzman, who is also CEO, has published an article about the general outline of the strategy (with source code so you can replicate the results!): Regime Shifts: Implications for Dynamic Strategies (corrected August 2012) by M. Kritzman, S. Page, D. Turkington]...


12

Sniffing (or stalking) algo indeed detects other algorithms. How does that work in practice? Imagine the order book for a particular equity is: Bid 1 = 99 (size 10,000), Bid 2 = 98 (size 25,000), Bid 3 = 97 (size 30,000), Offer 1 = 101 (size 10,000), Offer 2 = 102 (size 25,000), Offer 3 = 103 (size 30,000). So in the example above, the bids and offers are ...


11

I found this solid overview of different trading algorithms by Deutsche Bank Research: Trade execution algorithms Designed to minimise the price impact of executing trades of large volumes by ‘shredding’ orders into smaller parcels and slowly releasing these into the market. Strategy implementation algorithms Designed to read real-time market data and ...


11

In January 2020, Matteo Aquilina, Eric Budish, and Peter O’Neill from Britain's Financial Conduct Authority published this study, illustrating how "low latency" market participants can make money off of others. I suggest you read it, because it's very clearly written for the general public, and explains how markets work. I will first oversimplify ...


11

Is there a typical "half-life" of a strategy? This is a really subjective question, and I don't think any singular answer will generalize well. That being said, I will give some examples from personal experience. I have made hundreds of trading models in my career. I have only deployed 9 into live trading in the last ~25 years. Of those 9, 2 of ...


8

You would definitely have some advantage. High Frequency Trading is all about speed and the fastest traders wins. Oftentimes, winner takes all. The blog Sniper in Mahwah & friends digs into the state of the art of inter-exchange communication. The current state of art for reliable broadband connections are microwave dishes between major trading hubs such ...


7

The most commonly-known approach to this is described in Inferring trade direction from intraday data (1991) by Lee and Ready. You will find that the non-trivial part has to do with classifying trades that are reported inside the spread. I believe you will find that the Lee-Ready algorithm will outperform the naive midpoint reference approach suggested by @...


7

If I was in your position I would start to research how I can create a web server is C++ and expose calls to create a REST service. In other words, can you make your code status output to HTTP? From there, the rest should be easy. You would just need to create a GUI that can access REST services, which virtually all modern languages can. You could focus on ...


6

I ended up developing my own financial news API (real-time and historical) covering All newswires and press releases of all US listed companies (PR Newswire, Globenewswire, BusinessWire, etc) Journals (Wall Street Journal, Bloomberg, Reuters, etc.) All SEC filings (10Q/10K, 8K, 4, etc) + SEC press releases (e.g. SEC charges a company with fraud) ...


6

To be honest you're not likely to get a very satisfying answer to your question. Not because its a bad question, but because "regular people" can't just go hooking their home grown trading systems up to a live market. I'd like to start automating my trading strategies. First off you'll need a system that can interface with your broker. If you're not a ...


6

Let me try to answer: I have seen how equity trades are executed at the order book level. Let's say the price of the stock is 100 (last traded price). Let's say the order book is as follows: Bids: Bid1 = 99 (size = 10,000), Bid2 = 98 (size = 20,000), Bid3 = 97 (size = 25,000), Bid4 = 96 (size = 30,000), Bid5 = 95 (size = 40,000): total size = 125,000 stocks. ...


6

There are a number of price impact models which seek to predict the bias induced on prices by trading. There are also issues with some of these models (which I will mention later). Models Probably the earliest and most-known model is that by Torre and Ferrari (1997) which estimates the impact to be a multiple of the square root of trade size over average ...


6

Take a look at compilations such as 151 Trading Strategies. I wouldn't expect this information to be widely disclosed. After all, a non-profitable strategy is a supermartingale which means there is an opposing set of algos that is profitable as we speak. Secondly, many strategies are conditional upon a market regime, and could become profitable should the ...


5

TLDR: Massive expansion of credit fuelled by rehypothecation, a general shift to repo, then the scale tips and everyone pays as credit collapses. Quants were there, but I don't think they can be simply blamed for all the ills of the world. There is a general disagreement about what caused what, so some of this is guesswork. I'm marking this a community wiki ...


5

6 months is a reasonable estimate. Typically such strategies do not decay as in half-time but rather stop working in a discrete manner. Parameter tweaking can help, but for a limited period of time. To add to your list which is valid in itself: Infrastructure changes at the trading venue, in particular latency-related changes Market-making program changes ...


4

Trade matching is the process of 2 investment banks electronically inputting their respective trade details into an electronic trade matching platform; it is called trade matching because both parties are equal in this relationship. Conversely, where an investment bank has executed a trade with a buy-side firm (e.g. pension fund, insurance company), part of ...


4

These are the libraries I most prominently use for C++: QuantLib Boost C++ Libraries This is not specifically a library however it is extremely helpful, the Anaconda Compiler Tools. The Armadillo C++ library for linear algebra & scientific computing. The Intel Math Kernel Library for C++ (MKL). The Ta_Lib Technical Analysis Library has an API for C/C++...


4

These 2 sites are relevant: - The Whole Street (research aggregation) - Oxford Capital Strategies (strategy reviews)


4

Trading through an ECN is a good idea, FXALL is probably a bad choice since they have such a small market share. Currenex and Hotspot are both better. EBS (in EUR, JPY, and CHF) and Reuters (in GBP, AUD, CAD) have the largest market shares, but they both are expensive to set up and require monthly fees regardless of how much you trade, their liquidity in ...


4

Is there anything which can be done to account for the underlyings with no listed option contracts? Classical options pricing theory relies on the idea that any option contract can be simulated with the appropriate dynamic hedging strategy. Options pricing practice indicates that this is sort-of true. So one thing you can do is synthesize the given ...


4

Look for the Overnight LIBOR or OIS rates for each currency. It's easier to find LIBOR rates by the way, but OIS are closer to being risk-free. In a nutshell, LIBOR rates contain bank related credit risk which may induce bias your analysis. Also available for the USD is the fed funds rate and the ECB refinancing rate for the EUR.


4

Most of these classifications of aggressive trades are not so relevant anymore, due to smart order routers which execute aggressive parent orders using passive child orders, as Maureen O'Hara points out in http://www2.warwick.ac.uk/fac/soc/wbs/subjects/finance/fof2014/programme/maureen_ohara.pdf I am not sure what I would do if I wanted this information, ...


4

This is an interesting question. I would reformulate a little bit your question and try an attempt of answer of why using neural networks is not a good idea for predicting market direction. IMHO, one main reason would be that it is not possible to experiment a strategy without modifying the market behavior and thus it is impossible to repeat the same ...


3

There's some pretty basic frameworks for IB. One that's pretty simple to modify is http://sourceforge.net/projects/jsystemtrader/ . I haven't looked in a while but it uses only market orders. The development has gone on to a version that uses market depth. There's also things like Ninja Trader but paid per month. It's what I do and I just use java with ...


3

The predominant protocols/APIs offered by FX ECNs are FIX and ITCH. So you might want to look out for node.js implementations of these, e.g. nodefix. Without that ``extra'' layer, the trading venue that comes closest to your (bulleted) requirements would be Currenex with their STP connectivity, a RESTful API based on FIXML. I put `extra' in quotes because ...


3

What about frontend like MultiCharts or NinjaTrader? Or even a cheaper one like SierraChart or AmiBroker? There is also cTrader Automate (cAlgo) and ProTrader PTMC. All of these are specifically built for real time trading of derivatives, including hooking up to a broker like Interactive Brokers, Lmax, etc. And they have their own programming language with ...


3

Your aggregator should be coding not just to the FIX feeds but the specialized protocols. FIX just gives the bare minimum. For example, Hotspot's FIX certainly works but is throttled and doesn't have the full market data detail. You need their Itch. For Currenex, you need their Itch and Ouch. Your aggregator provider should also give impartial advice ...


3

I think spread midpoint will be more safe reference, after that if transaction price is higher from midpoint its buy, otherwise sell, if equal then not specified.


3

If your goal is to just send basic commands, and avoid rewriting you models, I suggest you to create a PID server in combination with a web/JavaScript site as GUI. The PID server monitors the PID’s of the strategies running on the server and executes the commands as they come. The server could consist of a webserver listening on port 8888 with a simple JSON ...


3

I am currently developing a position keeping system and I am very satisfied with my choice of language/libraries: 1) Pure GUI in C#. C# is very pretty language, and Visual Studio Express is a very good free IDE, where you can spawn all the buttons, lists and inputs you need. .NET is otherwise very versatile library for other stuff (built-in data structures, ...


Only top voted, non community-wiki answers of a minimum length are eligible