NMRMS User Guide

Step 1: Portfolio Construction

There are two ways to construction user’s portfolio. Users can upload their portfolio file or construct their portfolio with our stock database.

1.1 Upload Own Data

Users can optimize any portfolio that they upload online.

1. New upload: upload a new portfolio dataset.
2. From archive: choose pre-uploaded and temporarily saved portfolio data.

Tips:

The filename extension should be (.csv) or (.txt) with ‘,’ as separator.
The first row should be names of assets.
The first column should be a date sequence.
Each cell represents the price of an asset at a certain date.
An example of portfolio file can be downloaded as sample data.
Note that the start date and end date must be within the original dataset.

1. Set Data Window Size
   The data window size indicates the length of historical data used for estimating  assets’ return and covariance. Please make sure the data window is at least 4 times the rebalancing period. 
2. Set Rebalancing Period
   This parameter is denoted by the interval between two adjacent rebalances, which is the process of realigning the weightings of a portfolio of assets to maintain an original or desired level of asset allocation or risk. The shorter the rebalancing period, the more frequent the portfolio will be set to its optimal weights based on optimization algorithm.
3. Click ‘Add’
   User can add multi/different parameter sets for the simulation, optimization and comparison.
4. Click “Next”

1.2 Load from Database

User can construct the portfolio with our equity database.

1. First user need to set the start date and end date as the back testing period. And the data window size and rebalancing period for the portfolio construction.

2.In the stock selection page, we provide two methods to add stocks to user’s portfolio. The simplest method is searching stock by its ticker*.
*User can add stocks to white list by searching their tickers or companys’ name. All the stocks in white list will be added to portfolio even if they don’t fit the filters.And we have filters for user who have specific idea of the kinds of stocks which meet their standards and suit their strategies. For examples:

• Use ‘market cap’ to find large cap or small cap stocks
• Use ‘sector’ to find stocks in a particular industry
• Use ‘P/E (price-to-earning ratio)’ to select value or growth stocks

Multiple filters can be applied to help the user to find the stocks for their portfolio, and we also provide an easy way to delete all the applied filters all at once.

Notice some filters provide both ‘Percentile’ filter and ‘Min/Max’ filter to fit different needs. User can change it by clicking the filter name.

3.Stocks that have been selected by filters will show in the table below. And all these stocks will be added to user’s portfolio.
Notice selected stocks will be automatically propagate to the portfolios of following rebalancing dates, which means the portfolio will not change in the following rebalancing dates even if some of the stocks are not fit the filters.Step 2: Add portfolio-optimization algorithms

Step 2: Choose optimization model

In this part, we introduce 4 kinds of algorithms and correspondingly parameters first, and then we have a brief view towards other constraints.

1) 1/N algorithm

No parameter for this algorithm

2) Markowitz algorithm

1. Choose Returns Estimation Model from the following 3 methods: sample mean, equal mean and linear shrinkage (with Shrinkage Parameter δ).
2. Choose Covariance Matrix Estimation Model from the following 4 methods: sample covariance, equal correlation, linear shrinkage (with Shrinkage Parameter δ) and nonlinear
   shrinkage.
3. Input Risk Aversion Coefficient with positive value.
4. Set Position Limits with min and max value for selected asset (optional)

3) SOCP algorithm

1. Choose Returns Estimation Model from the following 3 methods: sample mean, equal mean and linear shrinkage (with Shrinkage Parameter δ).
2. Choose Covariance Matrix Estimation Model from the following 4 methods: sample covariance, equal correlation, linear shrinkage (with Shrinkage Parameter δ) and nonlinear shrinkage.
3. Input Risk Aversion Coefficient with positive value.
4. Set Market Impact with Square Root Impact Coefficient for selected asset (optional).
5. Set Position Limits with min and max value for selected asset (optional).
6. Choose Block List (optional).
7. Set Max Loan for selected asset (optional).

4) SAAM algorithm

1. Choose Returns Estimation Model with method Ledoit Wolf 2002
2. Choose Portfolio Returns Resampling Model with method block boostrap
3. Input Risk Aversion Coefficient with positive value.
4. Set Market Impact with Square Root Impact Coefficient for selected asset
   (optional).
5. Set Position Limits with min and max value for selected asset (optional).
6. Choose Block List (optional).
7. Set Max Loan for selected asset (optional).

※To set square root impact coefficient for an asset, tick the check box of the asset, fill in the number you want to set in the input box below, and click “Update”. Other optional constraints can be set similarly.

※If you want to set the same coefficient for every asset, tick the check box on the top left corner to select all, fill in the number in the box below and click “Update”. Other optional constraints can be set similarly.

Step 3: Configure diversification method and corresponding parameters (optional)

With optimization methods of Markowitz, SOCP or SAAM algorithm, users can choose Corvalan
algorithm for portfolio diversification.

1. Set Relaxation of Expected Returns Δr
2. Set Relaxation of Covariance Δσ

For more details, see :  Diversification Method

Step4: Run simulations and view outputs

1. Select the newly-added model under the data source
2. Click ‘To do’
3. Run stimulations
4. Report