An AI Fintech SME based in the UK aims to solve a significant unmet global need with its fully autonomous trading platform using advanced Artificial Intelligence models in the financial trading sector. It has the twin goals of increasing profitability and improving the work-life balance of traders.
The company is seeking collaboration with partners to form service agreements to test their autonomous trading platform in different market conditions.
UK-based AI Fintech SME utilise Artificial Intelligence (AI) models through the application of advanced machine learning algorithms in a software-as-a-service (SaaS) cloud environment to automate financial trading.
Many financial traders operate in high-stress situations and make decisions that are affected by their emotions, which can lead to significant underperformance in the market. Therefore, the client has designed and built a fully autonomous trading platform using advanced AI models that learn over time and gain experience without making emotion-driven trades would significantly increase the profitability of asset managers / holders and provide greater work–life balance to traders. Also, unlike other automated trading platforms, the platform does not copy human traders; rather, it uses deep learning for technical analysis and features selection.
The platform is a machine learning agent that maximises profits gained from trading in financial markets using state-of-the-art deep reinforcement learning algorithms. The program’s agent has demonstrated significant potential during simulations and back-testing. Without any human intervention or supervision, it succeeded in achieving multiple folds of the initial investment per year.
The SME seek partnerships, perhaps with investment management and equity fund companies, to trial the platform and execute a Proof of Concept (PoC) in simulated live-trading conditions through a Service Agreement.
- Type of partner sought: Ideally, investment and fund managers with experience in equity funds.
- Specific area of activity of the partner: The client seeks to build partnerships, ideally with investment management and equity fund companies, through the use of service agreements to trial the platform and execute a Proof of Concept (PoC) in simulated live-trading conditions. Although the client is not not offering remuneration for trialing the platform, all PoCs will be implemented for free and the company will handle all costs related to the PoC implementation and cloud hosting.
The platform provides multiple advantages and innovation:
1) Deep reinforcement learning algorithms can outperform human players in many challenging games. For example, in March 2016, DeepMind’s AlphaGo program, a DRL algorithm, beat the Go game world champion Lee Sedol four to one.
2) Return maximisation is the trading goal. By defining the reward function as the portfolio value change, the platform maximises the portfolio value over time.
3) The stock market provides sequential feedback. Accordingly, the platform can sequentially increase model performance during the training process.
4) There is no requirement for a skilled human to provide training examples or labelled samples. The platform uses standard market data (open, close, high, low, and volume) for each minute. All the technical indicators’ mathematical calculations are done within the platform, which reduces the dependency on external data providers.
5) The platform uses multi-dimensional data and can handle big data with no performance degradation issues.
6) Empowered by neural networks as an efficient function approximator, the platform can handle extremely large state space and action space.
Available for demonstration