What is the Axyon AI Platform?
Axyon AI Platform is our proprietary Auto-ML platform for financial time series. A highly automated process that explores and optimizes (i) a wide array of ML algorithms, including deep neural network models (ii) their free parameters, (iii) hyperparameters, and (iv) the selection of input variables, and produces an optimized ensemble of models Tailored for financial time series data of any kind and frequency.
What kind of AI models are used in Axyon IRIS®?
Our focus is not on individual models, just like for car manufacturers the focus is not on fixing individual cars but rather on designing and implementing a high-performing, efficient and automated assembly line for producing cars. And this process evolves over time through incremental improvements. At the moment, Axyon IRIS® strategies are powered by ensembles of supervised learning models including neural network-based (both tabular and sequential) and tree-based models. First, a large number of candidate models is explored with a hyperparameter search algorithm. Secondly, such models are optimally combined to constitute an AI model ensemble that is used for historical (out-of-sample) prediction generation and is ultimately deployed to production.
What kind of data is used in Axyon AI's models?
We ingest data of different kinds and from multiple sources. The main data types used to create Axyon IRIS® datasets are EOD and intraday market data, fundamental indicators, macroeconomic indicators, related indexes or securities (e.g. commodities, VIX, FX, etc.), sentiment indicators extracted from news and social media, options data, and analyst forecasts. In very specific cases and with selected partners, we support the possibility of including proprietary indicators that our client might have developed - we currently do this with our two largest clients.
Are predictions in Axyon IRIS® explainable? How?
We believe that the explainability of a Machine Learning model can be as crucial as its performance in many business applications for many reasons (trust, regulatory, technical, ethical, etc.). Our AI platform natively supports a state-of-the-art technique called SHAP (short for Shapley Additive Explanations) to decompose each prediction into the contributions of each individual input variable. In other words, for each input variable we can compute a (positive or negative) contribution, and if we sum all these contribution we obtain the model’s prediction. As the typical number of input variables per model is in the range of 200~500 features, to simplify the interpretation of these contributions we can group together all features belonging to the same semantic “category” (e.g. all features related to the fundamentals of a certain stock) and compute their aggregated contribution. By doing this, we can explain a prediction in terms of a small number (5-6) of “feature categories”, e.g. corresponding to classical financial factors, thanks to the fact that SHAP values are additive.
How is feature engineering performed?
Over time, we have created a feature store for financial time series problems that we maintain and continuously improve. Most of the data modelling work is carried out by our Quant Analysis team, whose work is integrated with our ML process, ensuring that every single feature can be computed with point-in-time data, is stationary, is expressed in a format that can be fed into supervised AI models, and it can be computed in live settings under time constraints.
How can artificial intelligence help asset management firms?
AI and machine learning enable fund and asset managers to save time and manage risk to protect their investments. It can also help businesses navigate challenging conditions by detecting anomalies in the market before any crisis occurs. By implementing AI, fund and asset managers can also monetize data and improve automation from the front to the back office.
What is an algorithm?
An algorithm is a sequence of instructions or commands carried out in a systematic way with the aim of solving a problem or performing a task.
The word “algorithm” refers to al-Khwārizmī , a famous 9th-century Persian mathematician who first defined the rules of algebra for its universal and applicable use.
What is Artificial Intelligence (AI)?
Artificial Intelligence (AI) is a branch of computer science that deals with the creation of intelligent agents, which are systems that can potentially reason, learn, and act autonomously.
What is Machine Learning (ML)?
Machine learning is a branch of artificial intelligence based on the idea that systems can learn from data, identify patterns and make predictions with minimal human intervention. There are many ways that machines aim to learn these underlying patterns.
If you want to learn more about how machine learning helps us improve the way investment is managed, check out our Research Line.
What is Deep Learning (DL)?
Deep learning is a subset of machine learning that is concerned with algorithms loosely inspired by the structure and function of the brain called Artificial Neural Networks. With accelerated computing and large data sets, deep learning algorithms are able to self-learn highly nonlinear patterns and make accurate predictions on unseen data. Techniques such as deep learning delegate to algorithms the choice of the best functional form or a probability distribution, with significantly better with fewer a priori assumptions. Deep learning technology underpins many of the predictive models that are included in Axyon AI products.
What is Natural Language Processing (NLP)?
Natural Language Processing is a branch of artificial intelligence that uses machine learning to help computers learn the meaning of texts. It is used to fill the gap between human communication and computer understanding and has several applications. Across the financial industry, NLP is used from retail banking to corporate investment: its applications range from risk assessment, sentiment analysis, portfolio assessment and document classification, among others.
What are Neural Networks, and how do they relate to AI?
Artificial Neural Networks are a type of AI algorithm loosely modelled after mammals' brains. They are composed of a large graph of interconnected processing nodes, or artificial neurons, that can learn to recognize patterns in the provided data. The learning process depends on the given task, such as classifying objects into categories, denoising dirty data, etc.
What is FinTech?
In theory, the term Fintech is quite simple as it comes from the combination of the words Financial and TECHnology. In practice, however, the true meaning of what is fintech goes far beyond. Fintech is used to refer to startups or companies that develop fully digital financial products, in which the use of technology is the main differentiator compared to traditional companies in the sector. It describes any technology that enhances financial services or enables new financial products and services to be offered. Fintech is a broad category that encompasses many different technologies, but the primary objectives are to change and improve the way consumers and businesses access their finances.
I don’t know how to code. Can I use Axyon AI’s solutions?
It does not require any coding or programming knowledge to access our web-based AI platform Axyon IRIS®. It has a user-friendly interface and can be accessed online from multiple devices. Alternatively, its results can be programmatically integrated into your investment process by using APIs or SFTP. Learn more here about how Axyon IRIS® can help you improve investments are managed.
I’m a student and would like to have a demo of Axyon AI’s platform. How can I request it?
We have a very strong connection with academia and we value the contribution of research to the development of our AI solutions. If you are a student, please fill in the form below with detailed information about your project and you will be answered as soon as possible.