MATLAB: Backtesting portfolio asset allocation

asset allocationbacktestingportfolio optimization

Hello,

I have 4 portfolio strategies I want to backtest. The portfolio strategies come from other 2 codes I created (mean-variance and mean-ES portfolio optimization frontier). Each of these strategies are basically just the weights of five different asset classes in the portfolio(s).

I want to compare the profitability of these four strategies for the period Jan 1st 2000 to May 1st 2014 evaluating the market value of the portfolios at every 10-day interval starting from Jan 1st 2000. All this assuming that I invest 1 million USD in every portfolio and hold the portfolio for the whole period mentioned.

My question is: How can I do this?

Thanks.

Best Answer

Assume that each column in the matrix Prices contains the time series of one your asset classes. Then calculate first the returns of the asset classes.

Returns = diff(log(Prices))

Now calculate the historical portfolio returns.

PortfolioReturns = Returns * PortfolioWeights;

Now let's see what happens to your million dollars:

Portfolio = 1e6 * [1; exp(cumsum(PortfolioReturns))]

Repeat this calculation for every portfolio.

Related Solutions

MATLAB: Backtest fcn and portfolio value

Hi Ando,

Unfortunately there is not a great way to do that using the current backing framework. You could try to work around the limitation by creating a fake asset in your prices timetable that represents incoming cash, and then have that asset double in value at each rebalance time step. You could then treat the growth of the fake asset as the cash contribution, pull it out, and allocate it with the rest of your portfolio.

However, this workflow is not recommended and it would mean your summary metrics (e.g. total return, Sharpe ratio, etc) would all be incorrect.

MATLAB: Efficient portfolios constraints, how can I add a particular constraint

The first constraint is easy to implement.

ConSet = protcons('PortValue', 1, NumAssets, 'AssetLims', -1, AssetMax)

where NumAssets is the number of assets and AssetMax is a vector with the upper boundary for the portoflio weights.

The two other constraints are a bit of a problem. You cannot order the optimizing function to use only a certain amount of assets. So there is no Matlab function for your problem. If your number of assets is small you could loop through all possible combinations of assets, optimize a portfolio and chosse the portfolio with the highest return for a certain amount of risk. Afterwards yoou repeat that process for the other portfolios of your efficient frontier, but you omit certain assets (according to your third constraint).

Best Answer

Related Solutions

MATLAB: Backtest fcn and portfolio value

MATLAB: Efficient portfolios constraints, how can I add a particular constraint

Related Question