Research
Improving the investment using AI
Research project at inbestMe
At inbestMe we work with academia (universities and doctorates) to achieve a self-adaptive forecasting module that will allow us to predict future values and an advanced investment tool based on machine learning and big data.
Title of the project
LLM-GENFRAMEWORK: AI-based intelligent assistant for developing and researching quantitative investment strategies with applicability to diverse business areas.
Description of the project
Creation of a unique solution based on Large Language Models and Retrieval Augmented Generation methods to support the creation, research and analysis of quantitative investment strategies, and also applicable to other areas. Based on the successes of LLM models and RAG methods, the solution will increase labour productivity in the creation of quantitative investment strategies, and in other areas related to data analysis and IT solution development.
We will create a generic LLM-GenFramework module to apply the above-mentioned techniques to various business areas, as well as a specialised LLM-Invest product designed to support the research, development and analysis of investment strategies.
Project details
Duration: 24 months
Start date: 01/03/2025
End date: 01/03/2027
Agreement No: E! 7764 LLM-GENFRAMEWORK
Partners
AI Investments, Poland http://www.aiinvestments.pl
Holisun SRL, Romania https://holisun.com
inbestMe, Spain https://www.inbestme.com
Budget
Total project budget: 1.597.156 EUR
Total inbestMe budget: 462.024 EUR
Co-financed by InbestMe: 185.676,88 EUR
Amount of the inbestMe grant (grant): 276.347,12 EUR
CIIP 2025 CoD 7 Calls: This project has received funding from the “Corresponding Program” program with co-financing from CDTI and the European Union’s “Horizon Europe” Research and Innovation Framework Programme.
Title of the project
GENDEG: Algorithms for identifying generalization capabilities and degradation in time of machine learning predictive models to improve AI Investments, InbestMe and Holisun current products and services.
Description of the project
The project
aims to create unique algorithms for identifying AI-based predictive model
degradation over time. Additionally, it will develop methods to assess AI-based
models’ ability to generalise performance in future. Implementing these
algorithms will lead to improved investment results for AI Investments and
inbestMe, as degraded models and strategies will be eliminated. Holisun will
benefit from maintaining high prediction accuracy over time. Furthermore, these
algorithms will aid in selecting predictive models that perform on
out-of-sample periods. The focus is on choosing models with the best chance of
achieving favourable results in the future for various applications.
Project details
Duration: 36 months
Start date: 02/02/2024
End date: 02/02/2027
Agreement No: E! 4691 GENDEG
Partners
AI Investments, Poland http://www.aiinvestments.pl
Holisun SRL, Romania https://holisun.com
inbestMe, Spain https://www.inbestme.com
Budget
Total project budget: 2.212.007 EUR
Total inbestMe budget: 647.924 EUR
Co-financed by InbestMe: 308.035,80 EUR
Amount of the inbestMe grant (grant): 339.888,16 EUR
CIIP 2024 CoD5 Calls: his project has received funding from the “Corresponding Program” program with co-financing from CDTI and the European Union’s “Horizon Europe” Research and Innovation Framework Programme.
Title of the project
SMARTY – Scalable and Quantum Resilient Heterogeneous Edge Computing Enabling Trustworthy AI
Project’s website: https://www.smarty-project.eu/
Description of the project
SMARTY invokes a cloud-edge continuum, made from heterogeneous systems, that protects data-in-transit and data-inprocess in order to offer a trustful fabric to run AI processes. The securitization occurs by employing novel accelerators for quantum resilient communications, confidential computing, software defined perimeters, and swarm formation, offering multiple layers of security. Semantic programmability and graph-management open the door to drag-and-drop approaches in deploying services in a fast and reliable manner.
Project details
Duration: 36 meses
Start date: 01/06/2024
End date: 01/06/2027
Grant Agreement Number: 101140087
Partners
CNIT, https://www.cnit.it/en/
Barcelona Supercomputing Center, https://www.bsc.es/
Italtel, https://www.italtel.com/
University of Stuttgart, https://www.uni-stuttgart.de/en/
Orange, https://www.orange.pl/
Nvidia, https://www.nvidia.com/it-it/
Bosch, https://www.bosch.com/
Continental, https://www.continental-automotive.com/en.html
CMPG, https://cmpg.io/
Budget
Total project budget: 31,999,656 EUR
InbestMe total budget: 650,000 EUR
This project is supported by the Chips Joint Undertaking (JU), European Union (EU) HORIZON-JU-IA
Title of the project
ADVISOR: Universal Auto-Adaptive Time Series Forecasting Framework
Description of the project
This project will research and develop an auto-adaptive forecasting module that will enable us to predict future values of a given time series with remarkably high accuracy. This software will be a completely new product in the market. It will be based on the latest most advanced artificial intelligence algorithms. It will also contain the exclusive automatic adaptation set module, which is a unique feature that is not yet available on the market. This software will accurately predict future values from time series data and can be used in a wide range of industries such as banking, financial investment, healthcare, retail, logistics, mobility and more. The software will be offered as a stand-alone product to other SMEs and various organizations who will be able to enhance their existing services and products and gain a significant competitive advantage.
Project details
Duration: 36 months
Start date: 01/10/2022
End date: 30/09/2025
Agreement No: E! 1278 ADVISOR
Partners
AI Investments, Polonia http://www.aiinvestments.pl
benchANT GmbH, Alemania https://benchant.com/
University of Oslo, Noruega https://www.uio.no
inbestMe, España https://www.inbestme.com
Budget
Total project budget: 1.923.630 EUR
Total inbestMe budget: 523.987 EUR
Co-financed by InbestMe: 209.594,80 EUR
Amount of the inbestMe grant (grant): 314.392,20 EUR
CIIP 2022 Calls: This project has received funding from the “Corresponding Program” program with co-financing from CDTI and the European Union’s “Horizon Europe” Research and Innovation Framework Program.
Title of the project
ALTO: an advanced investment tool based on machine learning and big data
Description of the project
This project will research and develop a software platform for advanced assets portfolio optimization and risk control against unexpected events. New application will allow SMEs, retail investors, investment companies and large companies to better manage their portfolios and protect their assets and also public agencies to monitor risk of financial crisis. Thus, we aim to use most advanced achievements in machine learning (ML) field (e.g. Alpha Zero Differentiable Neural Computer etc.) to assure highest accuracy.
The main goal of the project is to deliver capabilities of most accurate assets portfolio optimization and risk control with improved long-term performance by applying the latest achievements of Artificial Intelligence (AI). The main result of the project is AI Investments (AII) software platform equipped with visualization tool to help investors take more informed decisions. It will be implemented by public agencies in order to monitor overall financial risks.
The most advanced achievements in Machine Learning (ML) field (e.g. Alpha Zero Differentiable Neural Computer etc.) will be used to assure highest accuracy platform and to improve asset optimization and risk control. Last, but not least, a very important result of this project is to train people in the new, state of the art skills in machine learning field, as well as disseminate and stimulate research in that area of the European Union.
AII platform will be offered to the SMEs, investment companies, pension funds, retail investors, large enterprises and even government agencies as a complete solution supporting their assets portfolio optimization and protection against unexpected financial events (crisis). Moreover, the AII platform will lower the entry barriers for financial technology (FinTech) startups and SMEs and provide investment and portfolio management services. This will respectively increase the competition, boost the innovation in the financial area and benefit the general public.
The consortium of this project involves 4 partners, 2 R&D performing SMEs (AII and InbestMe) and 2 universities (Ulm and Oslo). Both SMEs are active on a huge market, i.e. AI in Fintech. The consortium has a unique combination of academic and industry partners, which allows for efficient application of the latest achievements in ML It will be led and supervised by academic partners to the industry solution. Academic partners will be responsible for scientific methodology and evaluation of algorithms and methods.
Project details
Duration: 24 months
Start date: 01/06/2019
End date: 31/05/2021
Agreement No: E! 12894 AII
Partners
AI Investments, Polonia http://www.aiinvestments.pl
University of ULM, Alemania https://www.uni-ulm.de
University of Oslo, Noruega https://www.uio.no
inbestMe, España https://www.inbestme.com
Budget
Total project budget: 1.227.342,19 EUR
Total InbestMe budget: 320.103 EUR
Co-financed by InbestMe: 128.041,2 EUR
Amount of the inbestMe grant (grant): 192.061,80 EUR
Press mentions
La Vanguardia (5/06/2019)
Europa Press (5/06/2019)
Diario Abierto (5/06/2020)
FundsPeople (5/06/2020)
El Confidencial Digital (5/06/2020)