Key points

• Quantitative investment mainly relies on data and models to find investment targets and investment strategies

• The advantages of quantitative investing include discipline, systemicity, timeliness, decentralization, etc.

• The shortcomings of quantitative investment include sample error and sample bias, strategic resonance, misattribution, black boxes, etc.

Detailed explanation of the concept

In recent years, quantitative investment has become increasingly popular as one of the more popular investment strategies. So what is quantitative investing? Simply put, quantitative investment is the process of using computer technology and using certain mathematical models to implement investment ideas and investment strategies.

Traditional investment methods mainly include fundamental analysis methods and technical analysis methods, while quantitative investment mainly relies on data and models to find investment targets and determine investment strategies.

Quantitative investment does not rely on personal feelings to manage assets, but rather reflects appropriate investment ideas and investment experiences in quantitative models, uses computers to process large amounts of information, summarize and summarize market rules, establish investment strategies that can be reused and repeatedly optimized, and guide the investment decision-making process.

In terms of application, quantitative investment covers almost the entire investment process, including quantitative stock selection, quantitative timing, stock index futures arbitrage, commodity futures arbitrage, statistical arbitrage, algorithmic trading, asset allocation, risk control, etc.

Advantages of quantitative investing

Compared with traditional investment methods, quantitative investment has both advantages and disadvantages. Among them, the main advantages of quantitative investment include the following points.

(1) Discipline

Traditional investments are largely influenced by human emotions such as greed and fear, and it is sometimes difficult to guarantee discipline in transaction execution.

However, quantitative investment generally strictly implements the investment instructions given by the quantitative investment model, and does not change them at will as investors' sentiment changes, so it has relatively strict trading discipline.

(2) Systematic

The systemic characteristics of quantitative investment mainly include multi-level quantitative models, multi-angle observation, and massive data processing.

The multi-level model mainly includes asset allocation models, industry selection models, and selected individual stock models.

Multi-angle observation mainly includes analysis of various angles such as the macro cycle, market structure, enterprise valuation, growth and profit quality, and market sentiment.

Massive data processing means that quantitative investment can obtain far more data and information processing capabilities than the human brain through computers, thereby capturing more investment opportunities.

(3) Timeliness

Quantitative investment can track market changes quickly and in a timely manner, continuously discover new statistical models that can provide excess earnings, and search for new trading opportunities. Quantitative investment is about continuously searching for valuation depressions and capturing opportunities brought about by incorrect pricing and erroneous valuations through comprehensive and systematic scans.

(4) Decentralization

The diversification of quantitative investment can also be said to rely on probability to win. This is reflected in two aspects: first, quantitative investment finds rules from historical data. Most of these historical rules are strategies that had a higher probability of winning in the past; second, they relied on selecting stock portfolios to win rather than winning with one or a few stocks. From the perspective of investment groups, they also capture stocks with a probability of winning, rather than betting on individual stocks.

Shortfalls of quantitative investment

After talking about the advantages of quantitative investment, here are a few shortcomings of quantitative investment.

(1) Sample error and sample deviation

Many quantitative investment strategies rely heavily on historical data, but historical data may not be sufficiently diverse and accumulated over a long period of time, so sample sampling may be erroneous due to too small amounts, or biases due to non-random sampling. Correlation rules obtained on this basis may fail once they leave the sample range, thus losing their referential nature.

(2) Strategic Resonance

Many quantitative strategies are similar to technical analysis strategies. Once a strategy is proven to be effective, its effectiveness weakens as the number of users increases and the strategy resonates.

(3) Wrong attribution

In the widely used multi-factor quantification strategy, the reason is inverse from data results. As long as enough factors are constructed, it is likely that a specific known result will be achieved.

However, when a quantitative strategy based on this multi-factor combination is used for actual transactions, it may fail due to misattribution. Because of the reason going backwards from the results, it is impossible to distinguish exactly which are the incidental factors; those are the decisive causal factors.

(4) Black box

Various quantitative strategies, including high frequency, hedging, or arbitrage, often have no intrinsic causal relationships; the effectiveness of these strategies is mostly based on the strong correlation of historical data. The logic of the strategy is that, according to historical data, if a 55% or more probability is effective, then as long as there is enough repeated data, the chances of winning will accumulate.

However, there is only correlation. Without understanding the internal causal relationship, investors cannot predict. Under what circumstances, history cannot guide the future. Like a turkey, the owner comes to feed it every day, but the last day comes to kill it.