Convergence algorithm with folding to accurately identify pivotal portfolios around the efficient frontier.
Ability to select portfolios after optimization for maximum and minimum risk, return and ratios as well as custom profiles.
Support for mixed long/short position portfolios as starting and optimized portfolios.
Optionally include a benchmark index or investment for comparative and benchmarking analysis.
Current and optimal portfolios are highlighted in the efficient frontier chart.
Perform a rolling back test of periodic optimizations to evaluate the subsequent value added of optimization at incremental time periods.
The market data downloading application includes a new function to evaluate under or overvaluation of securities based on a discounted cash flow valuation derived from prevailing consensus analyst earnings estimates.
In the rolling backtest, is there any overlap between an optimization interval and the subsequent interval during which the optimized weights are used to calculate performance? I'm a bit concerned, because total returns are just TOO good for re-optimization done every data interval. It almost seems that the optimization process uses the next period's data. I can furnish an example showing almost 60% annualized return over the past 7 years using an ETF portfolio containing only SPY, EFA, IEF, TLT, DBC and VNQ with weekly optimization. I know trading costs are not included, but is the ideal result too good to be true?
Hi Pete, thank you for your post on this. You can send though your template by attaching it to a reply when getting the notification email for this post if you wish.
The rolling optimization cannot be biased as each optimization set is independent of the others. If we run weekly optimizations using a back period of one year, each optimization uses the raw data for one year up until the week. Therefore there is no possibility that each optimization can be using biased data.