My Investment Philosophy:
1/ For any asset to have a positive Expected Return, the source of risk must be compensated, otherwise we are just paying away.
@pedma7 You don’t need a correlation estimate, you need a decent vol forecast which isn’t underestimating risk ex ante. Trying to build a factor model on an universe where cross sectionally sufficient breadth isn’t reliable will be a fools game, you would end up coming up with noise
@ethanrkho No one in systematic trading is building models to find one or two events where they make or break, it’s all about having as many independent number of bets as possible with half decent forecast power
@ethanrkho There is enough evidence of structural inefficiencies in commodity markets due to hedging demand imbalance, low correlation across markets and noticeable patterns rising due to seasonality and trend, which can be easily systematized with appropriate portfolio construction
@TCK_JRubano are you using any textbooks for the course? If not would appreciate if you have any book recommendation on the supply/demand dynamics for agricultural/energy markets.. :)
You've heard of crypto trend signals.
Have you wondered how they were created?
Today, I actually show you guys how to create a performant, scalable trend signal. Hint: It's going to be a smart ensemble of weak trend estimators.
Randomly giving out free articles for retweets!
@systematicls It might something as simple as a transformation function to generate position size or some smoothing applied on the model output to generate reduced turnover without sacrificing too much signal strength
@systematicls Any paper directly talking about alpha is usually sth which probably would have been decayed post publication, where I find reading papers helpful to come up with my own ideas are areas where readers would generally overlook…
@Brunoschwalbach Hey congrats on the publication! I wrote a very relatable idea recently, not portable alpha but more about treating the whole exercise as a risk budgeting problem.
https://t.co/CWq8WNppP2
@__paleologo FRED-MD snapshots contain seasonality adjustments and prone to revisions, I don’t see any mention of them using vintages snapshots for analysis