Stock trading signals

We developed various stock trading strategies on top of the EQB-Quant platform. Different strategies use different techniques: some uses technical analysis and some uses natural language processing and sentiment analysis. The strategies reports buy signal for different stocks at different timings. Note that the strategies are for research purpose, and you will be responsible for possible loss if you trade according to these strategies. Some examples include:

Generic placeholder image

Trading platform for the Chinese financial market

On EQB-Quant, you can design, backtest, simulate and live trade Chinese stock and future strategies. EQB-Quant uses the CTP interface to trade futures and the LTS interface to trade stocks. On top CTP and LTS, EQB-Quant provides a much more convenient abstraction to write trading strategies. You only need to write a strategy once, and EQB-Quant supports backtesting against all available historical data, simulation against exchanges, and live trading in the markets.

EQB-Quant is written in Python. Python is a easy language with many financial and machine learning libraries. You can easily inter-operate with Matlab and R from Python.

Setup the EQB-Quant platform

Generic placeholder image

Design and backtest trading strategies

Historical financial data is a big headache when working with trading strategies. The EQB-Quant platform offers full historical stock and future trading data, including tick level data. For stocks, EQB-Quant offers complete company financials. EQB-Quant also has a collection of financial news and social media financial blogs and reports, which can be used for market sentiment analysis. EQB-Quant offers hundreds of financial indicators. EQB-Quant also contains a translator from MetaTrader’s MQL4 language to Python, this provides easy access to thousands of indicators from MetaTrader.

EQB-Quant contains backtesters for future and stock strategies. The backtests approximate the corresponding markets well. The web-based strategy reporting and debugging facility greatly helps the strategy design process.

Strategy example

Generic placeholder image

Optimize and evolve trading strategies

As market condition changes, trading strategies must change accordingly. EQB-Quant offers various toolkits for strategy optimization, for example, machine learning based, genetic algorithm based toolkits. EQB-Quant contains a walk-forward analysis toolkit. EQB-Quant also comes with a strategy evolution toolkit, which can generate strategies that fit market conditions.

Generic placeholder image

Support cloud-based calculation and mobile-based applications

The EQB-Quant platform can be deployed in the cloud. All backtesting and optimization can be performed in the cloud. And the full strategy debugging facilities is accessible through a browser. Within a browser, you have access to the whole EQB-Quant platform. EQB-Quant also comes with mobile apps through with you can monitor currently running strategies, and can access to trading signals.

Generic placeholder image


Many of the EQB-Quant’s functionality can be accessed through RESTful APIs, including historical data, news, blogs, strategy signals, and even the chart drawing capabilities. You can easily integrate EQB-Quant into your own trading environment even if you are not using EQB-Quant.

REST API documentation

Generic placeholder image