{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/8a43cc069e2b4302ab85f9b738b8ed0c\" frameborder=\"0\" width=\"1658\" height=\"1243\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1243,"width":1658,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1243,"thumbnail_width":1658,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/8a43cc069e2b4302ab85f9b738b8ed0c-8b87ce9b198433fa.gif","duration":77.653334,"title":"Self-Evolving Agent for Predictive Stock Alphas","description":"This Loom describes building a self-evolving, self-learning agent to perform quantitative alpha research for trading signals. The speaker explains that alpha refers to predictive signals highly correlated with next-day stock returns, used to guide the trading desk’s direction. They use WorldQuant 101 alphas as an example, starting with stock data from 2010 to 2014, noting the published alphas still work well on that period. Then they shift the data period so the agent can find additional patterns."}