Название: Supervised Machine Learning - Linear Regression
Автор: Shefali Nayak
Издательство: Leanpub
Год: 2022-09-10
Страниц: 92
Язык: английский
Формат: pdf (true)
Размер: 10.2 MB

The book is intended to get you acquainted with the world of Supervised Machine Learning and does not assume previous knowledge of the field. The commonly leveraged Linear Regression technique used to provide predictions that are continuous in nature is detailed in the book. Sample Python code included!

If you are not familiar with machine learning or want a refresher course that covers everything you ever needed to know to get hands-on with Linear Regression, this is the go-to book for you. Graphical representations and numerous examples have been leveraged to enable effective learning and retention of the concepts read in the book.

At the end of the book, you should be able to identify where the Linear Regression model can be applied, follow the basic algorithm, test the underlying assumptions and evaluate model performance for a Linear Regression model with your data. In addition to covering the difficult concepts in an easy manner, this book also details techniques that enhance the predictive power of the model.

Supervised Machine Learning models build and train a prediction algorithm leveraging historical data comprising a known set of input variables. Since the future predictions are guided by the inherent data patterns that the machine has learned from the labeled data, it is referred to as Supervised Learning. When a fresh set of values is fed to the model equation; the algorithm predicts the most likely outcome basis a trend it has caught in the underlying data variables. The input of Supervised Learning Models is controlled and known; The modeling technique is classified as Supervised Machine Learning Models if the target (outcome) being modeled for predicting the fresh set of values is known and labeled for historical data.