1.
Marcos Lopez de Prado, 친숙한 교수 이름중 하나입니다. 이 분이 올린 트윗에 올라온 논문입니다. Marcos Lopez de Prado는 트윗을 통해 코로나19의 위기를 금융공학, 자산운용이라는 관점으로 해석하여 교훈을 계속해서 올리고 있습니다. 이런 내용을 총정리한 논문이 ‘Three Quant Lessons from COVID-19’입니다. 저자의 주장은 크게 세가지입니다.
Very few market makers experienced losses during the #COVID19 selloff. They learned their lesson after the flash crash of 2010, and turned to nowcasting for managing real-time risks.
COVID-19 should be the quant's Sputnik moment. Forecasting is the past. Nowcasting is the future pic.twitter.com/QQqm6gfDdk
— Marcos López de Prado (@lopezdeprado) April 2, 2020
What are the difference between Forecasting and Nowcasting? Is Nowcasting just short-term Forecasting?
Answers below, in a nutshell.
For additional details: https://t.co/ne5u5h9luN pic.twitter.com/ci5wYUnOCR
— Marcos López de Prado (@lopezdeprado) April 5, 2020
발표용 자료를 크게 세가지 주장을 합니다.
What lessons can we learn amid this crisis?
1. More nowcasting, less forecasting
2. Develop theories, not trading rules
3. Avoid all-regime strategies
2.
Marcos 교수의 트윗을 보면 코로나19 위기속에서 퀀트들이 맞닥뜨린 경험을 통한 교훈 및 이론적 근거를 알리는 내용도 많습니다. 우선 지난 시기 위기들을 분석한 논문을 소개하고 있습니다.Portfolio Management Research에 올라온 논문중 Financial Crisis가 주제인 논문들입니다.
Navigate your way through the current climate, our Financial Crisis Collection is open to all until 31st March!
Access the research online now https://t.co/JwP5jRHakr pic.twitter.com/ZQ0DstOLO3— Portfolio Management Research (@PM_Research_) March 25, 2020
또다른 트윗은 위기에 대응하지 못하는 전략의 약점을 어떻게 최소화할지를 다루고 있습니다. 결론은 기계학습기술을 도입하라는 내용입니다.(^^)
Many quant funds have performed poorly during the #COVID19 selloff, because they confound research with backtesting.
In the scientific method, the purpose of testing is to refute a hypothesis, not to help formulate it. Backtest overfitting is ubiquitous: https://t.co/bcUqxhRKkw pic.twitter.com/mi926ToRtu
— Marcos López de Prado (@lopezdeprado) March 22, 2020
Prior to commissioning the strategy, evaluate its probability of a false positive: https://t.co/E1EqoDRpMR
After its deployment, monitor the following:
* probability of alpha decay
* probability of strategy drift
* probability of a regime switchhttps://t.co/UVgCMHuBnU pic.twitter.com/0DSi5vqtDT— Marcos López de Prado (@lopezdeprado) March 4, 2020
3.
Quatpedia 블로그에 올라온 Modelling the Bottom of the Covid-19 Financial Crisis는 코로나19를 다른 관점에서 접근합니다. 코로나19의 위기는 전염병치료의 위기이면서 경제 위기이고 전염병위기가 해소되지 않으면 경제 위기 또한 해소되지 않기때문에 전명볌 예측이 무척 중요하다고 주장합니다.
The global pandemic of current scope is something that was experienced by only a few of the currently living people. We have some historical accounts of how it unfolded in the past, but otherwise, it is uncharted territory. It is a true Black Swan event – event that I believe was in nobody’s lineup of stress testing scenarios. But we can still try to get some understanding of the scope of the current situation.
The actual global crisis is a mix of 2 crisis. The first one is the health-care / pandemic crisis, during which millions of people will be infected, and unfortunately, a lot of people will die. The second crisis is the economic crisis/recession, which will follow simultaneously with (or soon after) the first one (due to the decrease in worldwide supply and demand).
The second crisis cannot end before the first one is solved. It is impossible to predict how the world will look like in three months, which health care measures and economic stimulus will be adopted. But we can say that the current situation will get worse before it is better. We cannot exactly say when the market bottom will occur, but at least we can try to model the minimum time needed for things to get under control during the pandemic. And we can say that the economic situation will probably not get better before pandemic will be under control.
단순히 생각해보더라도 비교적 정확히 전염병위기를 예측할 수 있으면 사전에 경제적 행동을 할 수 있고 이를 통해 이익을 얻을 수 있지않을까요?
