{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/72fb3eaa0ce64e309e40c7b7bcef15ed\" frameborder=\"0\" width=\"1418\" height=\"1063\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1063,"width":1418,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1063,"thumbnail_width":1418,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/72fb3eaa0ce64e309e40c7b7bcef15ed-366717ef562a3214.gif","duration":248.501,"title":"Forecasting Latency Spikes with Simulacrum 📈","description":"In this video, I demonstrate how to use our Simulacrum platform for forecasting latency spikes in cloud services, using real data from a reliability monitoring company in New York. I walk you through the process of installing the Simulacrum SDK, generating an API key, and utilizing 85% of the dataset as historical data to predict the remaining 15%. By defining a forecast horizon and using our foundation model, I show how quickly we can generate accurate forecasts. The results, which I plot for you, indicate a strong correlation between the original and forecasted data. I encourage you to follow along and try this process with your own datasets."}