From the course: LinkedIn AI Academy AI-100: 1 Demystifying AI
Join today to access over 23,200 courses taught by industry experts.
Evaluating models and choosing the best
From the course: LinkedIn AI Academy AI-100: 1 Demystifying AI
Evaluating models and choosing the best
- [Instructor] In the last video, we learned about logistic regression, which enables us to build probabilistic models for classification so that we can obtain probabilities of a class that a new data point might belong to. We can compute that probability, but often in the end, typically a decision has to be made. Is the loan approved or not? Do we recommend a job to a member or not? For a machine learning practitioner, this means she or more likely, the classification model that she built will have to make a binary decision using the probability obtained from the model. A simple mechanism to do that is to have a threshold. For example, if the predicted probability is more than a threshold, say 0.5, then we will classify the data point into one class. If the probability is less than the threshold, then we will classify into the other class. Our framework depends on a mechanism to measure the error in our prediction.…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.