Linear regression for machine learning

Day 2, 1:00-4:30 pm (lecture and exercises)
Winnie Wezi Mkandawire

Linear Regression is one of the fundamental supervised-machine learning algorithms. While it is relatively simple and might not seem fancy enough when compared to other Machine Learning algorithms, it remains widely used across various domains such as Biology, Social Sciences, Finance, and Marketing, among others. It is extremely powerful and can be used to forecast trends or generate insights. Thus, I simply cannot emphasise enough how important it is to know Linear Regression — its working and variants — inside out before moving on to more complicated ML techniques. The simplicity of linear regression model can be attributed to its core assumptions. However, these assumptions introduce bias in the model which leads to overgeneralisation/under-fitting.

In this session, we will discuss the linear regression algorithm, how it works, and how you can best use it in on your machine learning projects. We will also cover the representation and learning algorithms used to create a linear regression model, and how to best prepare your data when modelling using linear regression. During practical session, we will analyse marketing data to provide insights about how expenditure on various types of advertising affects bottom-line revenues.

Speaker biography

Winnie Wezi Mkandawire is an interdisciplinary research-oriented free-lancing early career Bioinformatician/Data Scientist; a recipient of young researcher’s membership award for the American Association for the Advancement of Science, 2020; and a member of women in Data Science and women in Machine Learning, Massachusetts, USA.

She pursued MSc in Bioinformatics and Computational Science majoring in Data Science (Fulbright Scholarship, Worcester Polytechnic Institute, USA, 2021), MicroMasters in Statistics and Data Science (Massachusetts Institute of Technology (MIT), 2021), Postgraduate diploma in Bioinformatics (Kamuzu University of Health Sciences (KUHeS), yet to graduate), BSc in Biomedical Sciences (Mzuzu University, 2014), and is currently pursuing PhD in Basic Sciences with a major in Bioinformatics from University of Massachusetts Medical School (UMMS). Winnie is a multi-grants awardee in both independent as well as collaborative research projects and has worked with both national and international research and academic institutions on various interdisciplinary projects which employed the application of Data Science techniques. As a Data Scientist, Winnie has worked on various projects on the application of machine learning, deep learning, Natural Language Processing and Computer Vision—to solve various problems in the medical, health, business and agriculture sectors. One of the projects she worked on was application of a novel semi-supervised learning algorithm to elucidate mechanisms underlying drug resistance in HIV.

Her research interests are in the application of statistical, machine learning and deep learning methods in descriptive, diagnostic, predictive and prescriptive analytics. She believes interdisciplinary multifactorial approaches can be a better key in addressing most challenges affecting the world today.