Speaker 1: Hello and welcome back to Data Science Wednesday. My name is Tessa Jones and I'm a data scientist with Decisive Data and today we're going to talk about predictive analytics and what it can do for you. Predictive analytics fits into the spectrum of analytics that we've talked about before, starting with descriptive which is the most basic of the analytics is basically just cleaning, relating, summarizing, and visualizing your data. Really getting to the questions about what's happening in my business and then there's diagnostic which is really getting down to why things are happening, what's causing my revenue to decline or to increase, how are things related, things like that. So if you've got a good base in both of these then we're ready to move into predictive analytics which is going to dive into what's going to happen in the future which is super powerful. If you're a business person and you want to be able to make good business questions, if you have at least an idea of what might happen in the future, your answers are already going to be a little bit better. So let's dive in. So let's go with an example because that just makes it easier to kind of flow through what's actually happening here. So let's pretend that we are grocery store owners and if we're already talking about predictive analytics, you should have a pretty good grasp on descriptive and predictive and diagnostic analytics. So you probably already have a decent dashboard that really tells you what's happening in your business right now. So something like this where you have something here that tells you revenue by different departments like foods, meats, or foods and pastry, or how your sales changes by product or over time, things like that. So you have an idea of what's happening in your business but now you really want to know what's going to happen in my business. So one really common question is how many of a given product am I going to sell for every store? Because this can really give you answer questions around how you're going to support supply chain processes or how you're going to manage the profits that you're going to have, things like that. So the first thing we need to do is talk about what happened in the past. We really can't do anything or predict very easily unless we know or at least have an idea of what's happened in the past. So here we have three lines in black that represent basically historical data. Each line here is one year worth of sales for a given product and then the green line here is the current year and here's today and if we build a predictive model it's going to tell us what's going to happen for the rest of the year. So if this is all set up and we build a model, basically we mix this information with all the data that's really clean and well organized. We mash it together with a bunch of mathematics and coding and basically we pop out some results and it shows up in a visual like this where you have these are the sales that we have had and these are the sales that we think we're going to have. So a business person can look at this chart and say, wow we need to put a lot more products to this store because I see sales are going to increase or our profit margins are going to be way higher than we thought so we can start a new program. Things like that. You can really start to get innovative with your business decisions. So let's pretend we've built this model and it's been running for a year and now we want to know how well is this model actually performing. So down here we have a chart that shows in black what we actually sold and then in green what we thought we were going to sell. And we see that there's a couple of pretty big misses. Right here we sold way more than we thought we would which leaves risk to you know missing out on inventory. Or here we predicted we would sell more way more than we did. So both of these are kind of misses and so we need to go back and look at the data and understand what assumptions we applied that were maybe a little bit wrong or applied incorrectly or look at the data. Maybe we weren't accounting for something and we kind of reorganize that and incorporate it into the model and then we redeploy it and then we have a better model. This cycle can you know happen a couple times or it can happen many times. It really depends on the data. It really depends on the objective. It depends on a lot of different things. But we do try to minimize the number of times that we're having to iterate through this before we can have a really sound predictive model. So that's predictive analytics in a nutshell. Basically once you have a solid foundation of descriptive and diagnostic analytics we can really start pushing forward with predictive analytics. And then next week we're going to start talking about prescriptive analytics which really gets to the questions of okay now that we know what's happening in the future what do we do about it. I'm Tessa Jones and that's a reindeer.