G2Q Computing

Industrial companies deal with optimization and machine learning problems that quickly become too complex to solve without greatly simplifying the problem. Furthermore, as data and operational constraints grow, computation becomes a bottleneck that slows decisions and increases costs. G2Q addresses this by combining quantum and classical computing in a practical, scalable way, helping organizations improve efficiency by solving large optimization problems with less simplifications and improving training of Machine Learning algorithms to perform better with less data. Our integrated solution allows to solve : - Anomaly detection problems in financial crime and engineering: by solving large optimization problems we can obtain better results than using just a machine learning based approach because we can mantain high true positive rates without increasing considerably the number of false positives - Physics informed Machine Learning: . quantum correlations can capture subtle physical interactions and patterns that cannot be captured by just using classical machine learning algorithms - Portfolio optimization problems: Greater the number of assets and discrete constraints involved, the more difficult the problems becomes to be solved in reasonable times. By distributing the optimization problem, we can help to include more financial assets and decisions in order to improve the mix of financial assets required to meet an investment/risk goal. - Large scheduling or logistic problems: For problems where large fleets or personnel need to be optimized within a framework of multiple constraints, enabling to efficiently distribute the large optimization problem on HPCs can allow to achieve better solutions with less computation time .