The Base or Protocol Layer

The Protocol layer is the fuel for the AQTIS ecosystem. It’s here that our quant and AI technology is hard at work searching for ways of generating yield. Below we explain the constituent parts of the Base layer.

Full-Spectrum Data Mining

Acquiring the best market data available allows us to ensure our strategies remain agile and accurate. To achieve this, we use data purchased from third-party providers, which offer comprehensive historical data across multiple exchanges for all metrics and assets they cover, in their finest resolution.

This approach enables us to access tick data from various exchanges and identify patterns in their behavior. However, the data we receive is completely raw, meaning there is work to be done to ensure errors can be removed and outliers can be assessed.

Once we have this clean and structured data, we can develop multiple custom metrics or indicators that are unique to our systems.

It's important to note that we cannot resell raw data (even after processing) as it would violate the terms and conditions of our data providers.

Quant Analysis

Our approach involves utilizing our custom indicators and data to make informed decisions. This is achieved by analyzing market data and applying machine learning models, focusing on two main aspects: optimizing the parameters of our analyses and predicting the next likely market event.

Liquidity Optimization

This involves two key strategies: Firstly, we aim for the most optimized allocation possible to minimize directional risks (such as avoiding putting 100% liquidity in a single trend-following model) while being aggressive enough to maximize profits. We use a model that measures risk-adjusted returns for this purpose.

Secondly, we focus on selecting the right assets to trade with and optimize position sizes to minimize market impact and avoid issues like slippage. We address this by trading the most liquid assets (in terms of volume and order book liquidity) and optimizing position sizes accordingly.

Execution Strategies

We implement our trading models by optimizing the entry and exit points of our trades. This involves careful analysis and execution to maximize efficiency and profitability in each trade, ensuring that we enter and exit positions at the most opportune moments based on our models' predictions and market analysis.

AI-Confluence Optimization

By utilizing all our models and data, we can adjust allocations when there's a confluence in our systems. Essentially, this means when multiple indicators or models agree or present a cohesive narrative about a market trend or opportunity, we strategically modify our asset allocation to capitalize on this synergy. This method leverages the combined strength of our analytical tools and data insights to make more informed and potentially profitable trading decisions.