Hacker News Reader

So many use cases! Take the course! You can use regularization to learn from small datasets by penalizing learning extreme biased feature weightings.

For finding a use case or at work just think of any normal problem like UI or ux design, or showing someone an enjoyable loading screen or funny picture, anyone can make something okay but to solve a problem close to optimally you start to need to gather data and do ml/ai

View on HN

Well, for example, can I look at the company's sales performance over the past 24 months (along with various factors such as number of sales staff on the field) and accurately predict its numbers next month?

Where would I start with this? Is this even an ML problem?

Time series data is hard, especially without lots of training examples.

Consider looking into traditional forecasting methods as a baseline. AR(I)MA based approaches with seasonality might actually be fine for you.

However, it all changes if there are structural breaks in your dataset. Look into Rob Hyndman's free online book (https://otexts.org/fpp2/) for an excellent introduction into timeseries forecasting.

Reply on news.ycombinator.com