Select Page

Hypersphere

ML to serve people in investment decisions

Why do we actually need ML algorythms?

We Believe that ML algorythms are more effective than Humans. As soon as ML can substitute humans in simple tasks like image and speech recognition, as well as more sophisticated ones such as self-driving cars or bots like Siri. ML should also work well with price predictions on financial markets.

Machine Learning Algorythms (ML)

Machine learning (ML) focuses on the development of computer programs that can learn for themselves, given the collection of examples (data) as an input and the goal that needs to be met as an output. Deep learning is a particular kind of Machine learning. It is based on neural networks, which can be briefly described as the artificial representation of the human brain. Deep learning neural networks are capable of learning to focus on the right features by themselves, making the analysis better than what humans can do.

Developing ML

Developing of an ML algorythms consists of three tasks: gathering data, choosing deep neural network architecture (or a neural network model), and training it on data. Usually, training is a time consuming and expensive process. In order to build just one version of an effective deep neural network, it often takes a week to train using special machines equipped with GPUs. The other challenge is where to get a reliable dataset for training. These datasets are usually not publicly available and are in possession of companies and institutions who gather them in various ways. In some domains, there could be absolutely no datasets available.

Hypersphere ML is build up from three modules

Blue Sphere ML

This ML module predicts stock prices based on quarterly financial statements of companies.

%

Progress

Orange Sphere ML

The second ML module predicts stocks prices based on price patterns and technical analysis.

%

Progress

Green Sphere ML

The third ML module uses open social sentiment data which could be gathered across internet to predict prices.

%

Progress

Latest articles and news

Why stocks prices do not always reflect companies real value?

If you ask yourself a question is a share price reflects company’s performance? The answer is not easy to come because to get it you have to compare simultaneously many company’s figures and parameters from financial reports together with stocks price movements.
What does Financial Statment and Value Stocks means for portfolio investor?
How to apply Portfolio investment in stocks based on artificial intelligence (AI).

Is Artificial Intelligence better than human now?

Is Artificial Intelligence better than human now? The answer is Yes and No. In tasks such as evaluating huge amounts of companies financial statements data AI is already better. In building new evaluating models for companies assessment humans are still better for now. To generalize AI is more accurate, fast and cheap in routine simple and repetitive tasks especially where you can scale up. In our case, it is predictions of equities prices based on companies financial statements, technical analysis of shares prices, and social sentiment analysis. So we can expand the use of AI in portfolio investments, stocks trading.

Join US

Contact

Mail

team@hypersphere.pro

Address

10315, Estonia, Tallinn,
Randla tn 13-201