Stubble burning in neighbouring states and countries is one of the big ones
Secondarily it's vehicular and industry emissions. There are MANY factories in Delhi and they all expel their industrial wastes into both the air and water of the city.
nice to see someone tackling the pain points of foundation models for time series forecasting.
i'm curious, how do you handle concept drift in the data? do you have any built-in mechanisms for detecting when the model needs to be re-trained or updated, or is that something the user needs to handle manually?
I can only speak to our experience. Once you get under the hood, you find that this is a hard problem to solve.
There are also a lot of workflows that involve documents in every sector and every function. In other words, the opportunity is massive.
For our product, our customers are either internal engineering teams or folks building products that require document extraction but don’t want to invest time in it.
Any company that works with invoices from a number of suppliers. We had to solve this problem at DigiBuild, where every supplier seemed to have totally unique invoice formats (and even the same product names could differ between two suppliers.)
reply