Course Preview: Imperial Business Analytics: From Data to Decisions

19 August 2022

[Video Transcript] Imperial Business Analytics: From Data to Decisions

Ready to Learn More? Apply to Enrol in the Business Analytics: From Data to Decisions from Imperial College Business School Executive Education

Hello and welcome to this programme. We're really glad to have you on board on our analytics journey. The coming weeks will be intense. They may, at times, be a little strenuous even. But we are sure they will also prove immensely rewarding for your future career and your understanding of how data drives modern organisations.

I am Alex Ribeiro-Castro and I am a Teaching Fellow and Data Scientist at Imperial College where I'm also an academic member of our Data Science Institute. And I've also been working in the industry as a practitioner in the last four years where I worked as a scientist in fintech, energy tech, health tech and recently even also in education tech, which concerns the tech aspects of online education.

My academic background is in physics and mathematics. So, problem solving, crunching numbers with computers and looking for patterns in data sets has always been a big part of my daily professional life. And these three skills are core to the modern-day business analytics practitioner. I'm a graduate from UC Santa Cruz -- 'Go slugs!' -- and I have been a research member at the Fields Institute in Canada too.

And I'm Wolfram Wiesemann. I did my undergraduate studies in Darmstadt, in Germany, where I studied computer science and management. I then came to the computing department of Imperial college to do my PhD. After some post-doctoral visits at Princeton University and Columbia University, in the States, I returned back to Imperial College to join the Business School in 2013. At Imperial, I'm a professor of Analytics & Operations and I'm also the academic director of our on-campus business analytics master's programme. My research interests lie in the intersection of optimisation and machine learning, which happen to be the two parts that I'm also teaching on this programme.

Together we'll spend the next couple of weeks exploring the areas of descriptive, predictive and prescriptive analytics, pulling together the theory and methods from computer science, statistics, machine learning and optimisation to show you how to store, process, analyse and draw insights from data.

We split this course into four parts.

In part 1, we'll brush up on Python. If you're a seasoned Python user, great! This part will serve as a quick refresher. If you're new to Python, don't worry. This part will get you up to speed to use Python for analytics problems.

In part 2, we will cover the field of descriptive analytics, which allows us to explore and visualise data.

Part 3 will cover predictive analytics, which covers machine learning methods such as nearest neighbour methods, decision trees, support vector machines and clustering.

In part 4, finally, we'll explore the optimisation techniques underlying prescriptive analytics, which allows us to take the informed decisions based on data.

Alex, what is your favorite part of this class?

I think I'm really excited about the Python module. Even for those people who have seen it before, it is really like a really powerful tool for their tool bag, and they're going to be able to do simulations and do models and really act like a real data scientist or business analyst.

How about you?

Well, you know me, right? I'm biased. I have been working on optimisation theory since 2002. So, that's clearly my favorite part, part 4 of this programme. But that said, over the last couple of years, I've been working on machine learning a lot. So, I'm enjoying this part as well.

That's cool.

So, we all know you have a legacy of being a very fun guy. So, perhaps, with our audience, can you share one of your favorite data science jokes?

Oh, there are so many. Right. There's one that is inspired by a comic strip from XKCD. Where you have two friends, they're talking about data science. And friend A asks friend B, 'So, how do you do data science?', and friend B answers, ’Well, you know, put in a box, some linear algebra, some probabilities, some machine learning models, and toss in some data, shake it up and you're going to get some answers on the other side'. And then friend A asks again, ’Well, what if the answers are wrong?’. ‘Well’, friend B answers. 'Well, you just have to shake it again'.

So, that's the punch line.

Please don't switch off. Join us for the journey over the next couple of weeks.

[End of Video Transcript]