Methods for Simulating Multi-dimensional Data for Financial Services Recommendation
Methods for Simulating Multi-dimensional Data for Financial Services Recommendation

Summary/Abstract: This study is part of bigger research about self-learning systems for management of individualized investment portfolios. In this research we present several approaches for generating multi-dimensional synthetic data in conformity with the business logic, correlations, previous datasets, concatenation, neural networks, etc. Each approach is described algorithmically, and a brief comparative analysis is conducted at the conclusion of the paper. All described approaches rely to a different extend on real data as input – whether aggregated distribution or partially available real data to be enriched horizontally or vertically.

• Details
• Contents