Simply put, quantitative stock picking is an investment methodology that uses quantitative methods to construct a model and then select a portfolio of stocks with the expectation that the portfolio will outperform the benchmark return.

What are the risk characteristics of quantitative stock picking?

We'll take two typical strategies in the market that utilize quantitative stock picking as examples:

A market-neutral strategy

For a market-neutral strategy, the goal is to build a portfolio of high-alpha stocks through quantitative stock picking and to do a hedge against stock index futures. The goal is to strip market risk from the stock portfolio and harvest pure alpha returns. So a standard pure market neutral strategy should be less affected by market volatility, and then stable to get a good excess return. So in general the neutral strategy relative to pure equity long products retracement risk is smaller, the volatility is smooth, the maximum retracement is generally smaller, belongs to the relatively more robust investment strategy.

Second, the index enhancement strategy

The market is now more mainstream index enhancement strategy is mainly evolved from the original market-neutral strategy, in order to be able to improve the efficiency of the use of funds and wrestle for a higher return, the market-neutral strategy in the stock index futures hedging part of the removal of the construction of the stock directly pure long portfolio, the use of quantitative stock selection methodology to select the basket of stocks, tracking indexes, and control tracking error. Control tracking error. The goal is to obtain a higher return than the market index under the premise of assuming market risk, not only to obtain the pure alpha return provided in the neutral strategy, but also to obtain the return brought by the market itself.

There are two main types of index-enhanced products, CSI 300 index-enhanced and CSI 500 index-enhanced, with relatively more products tracking the CSI 500 index. Because of the removal of stock index hedging, index-enhanced products are fully exposed to market risk, in order to fight for higher returns. So index-enhanced products are characterized by high risk and high return. In general, the index tracked by the product will follow the fluctuations of the same up and down, but generally higher than the index in the upswing, while in the downswing than the index loss less, although the overall volatility of the strategy is relatively large, in the investment period may also be a large retracement, but due to the index-enhanced products compared to the purely neutral products more efficient use of funds and have a stronger compounding effect, in the absence of great risk in the market, it is more likely to obtain a higher return than the market. However, due to the more efficient use of capital and the stronger compounding effect of index-enhanced products compared to purely neutral products, it is more likely to achieve higher returns than neutral products without significant market risk.

The most common quantitative stock picking models

The more mainstream quantitative stock picking strategies in the market can be divided into two categories: the first is fundamental stock picking, and the second is market behavior stock picking. The fundamental stock selection models are: multi-factor model, style rotation model and industry rotation model. Market behavioral stock selection models include: capital flow model, momentum reversal model, consensus expectation model, trend tracking model and chip stock selection model.

Institutions engaged in quantitative investment in the market use a variety of quantitative stock selection models to build stock portfolios, through the use of modern statistical and mathematical methods, from the massive amount of historical data to find a variety of "probability" strategies and laws that can bring stable returns on investment portfolios, on this basis, the synthesis of factors and models summarized into On this basis, we synthesize them into factors and models, and then invest independently in accordance with these quantitative model combinations in a disciplined manner. Among the many stock selection models, the multi-factor stock selection model is a quantitative stock selection organizations use more of a multi-factor model basic principle is to use a series of factors as a stock selection criteria, to meet these factors of the stock will be bought, do not meet the sell.

The core principle of the multifactor model is to find those factors that are most relevant to a company's return. There are two main differences at the core of the various multi-factor models, the first being that the factors chosen may be different, and the second being that the combinations and weights assigned to the factors will vary. Combining these two points will result in different organizations ultimately selecting different portfolios of stocks. Generally speaking, the specific stock selection methods of multi-factor stock selection model are divided into two kinds of scoring method and regression method.

The scoring method is based on the size of each factor to score the stock, and then weighted according to a certain weight to get a total score, according to the total score and then screen the stock.

The regression method is to use past stock returns to regress multiple factors to get a regression equation, and then substitute the latest factor values into the regression equation to get a prediction of future stock returns, and then use this as the basis for stock selection.