Time-series

Portfolio optimization is a critical tool for modern investors willing to maximize their capital utilization in the market and expected returns. Many portfolio optimization techniques are based on different variants of constrained quadratic programming formalizations, taking as inputs expected asset returns, forms of risk metrics (like covariance matrices), and transaction costs.

Time series processing is a well-known and extensively researched problem. Moreover - many people naturally understand, what a time series is, and how it is structured. Things start to get complicated once you are about to prepare time-dependent data for modeling with neural networks. Three-dimensional structures are not that easy to imagine initially.