# Factor Models and Portfolio Construction [Introduction]

* According to Chincarini & Kim, *Quantitative Equity Portfolio Management (QEPM) is organised around the following 7 tenets (or principles)

- Markets are mostly efficient.
- Pure arbitrage opportunities do not exist.
- Quantitative analysis creates statistical arbitrage opportunities.
- Quantitative analysis combines all the available information in an efficient way.
- Models should be based on sound economic theories.
- Models should reflect persistent and stable patterns.
- Deviations of a portfolio from the benchmark are justified only if uncertainty is small enough.

The basic premise of modern financial economics is that the average return of a stock is the payoff to the shareholder for assuming relevant risk. Factor models express this risk-reward relationship by linking average stock returns to the

*factor exposure*: the stock’s exposure to the risk that the factor represents and*factor premium*: the payoff for each unit of exposure to the risk .

There are three generic factor models in QEPM that are used to determine how stock returns and risk vary with factors – the fundamental factor model, the macroeconomic factor model,and the statistical factor model,- the main features of which are summarised below.

**Steps toward building a quantitative portfolio :**

- Factor Choice
- Data decision (timeseries vs cross section)
- Factor exposure
- Factor premium
- Expected Return
- Risk decomposition (diversifiable vs systematic risk)
- Forecasting
- Security weighting

The following flowchart is a brief overview of the portfolio construction process :

ok

For much more detailed information and practical implementation of portfolio optimisation in R, visit the systematic investor blog here http://systematicinvestor.wordpress.com/