You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
Automated high-frequency trading has grown tremendously in the past 20 years and is responsible for about half of all trading activities at stock exchanges worldwide. Geography is central to the rise of high-frequency trading due to a market design of “continuous trading” that allows traders to engage in arbitrage based upon informational advantages built into the socio-technical assemblages that make up current capital markets. Enormous investments have been made in creating transmission technologies and optimizing computer architectures, all in an effort to shave milliseconds of order travel time (or latency) within and between markets. We show that as a result of the built spatial configuration of capital markets, “public” is no longer synonymous with “equal” information. High-frequency trading increases information inequalities between market participants.
In the age of automation, trading and market making is about estimating the fair price of automated trading system research and development projects. This requires a new methodology to arrive at such a fair price. A real options framework is a natural choice. In this paper we review a methodology for automated trading system R&D and present a practical real option model for valuing such projects so as to enable rapid strategy cycling.
Sixer
The confusion matrix is widely used for measuring the performance of discrete state predictive models ('classifiers'), however it fails to convey their economic utility for algorithmic trading. As a result, extensive backtesting must be performed and it can be difficult to attribute the P&L to the machine learning method. This paper introduces the concept of a 'trade information matrix' to attribute the profit and loss of classifiers under execution constraints, such as fill probabilities and position dependent trade rules, to correct and incorrect predictions. Such an approach is especially useful where execution constraints play a significant factor in alpha generation, such as high frequency trading. We further find through backtesting on Level II T-bond and E-mini S&P 500 futures history that machine learning methods have utility for market making but find no evidence to support the use of machine learning for market taking. Our conclusion is that while machine learning based price prediction may translate into economic utility through avoiding adverse selection in market making, it provides little if any advantage in gaining queue position, which is also a significant factor in strategy profitability.
Good book
Thank you