Welcome to this course on introduction to optimization models for decision making. So why are we talking about optimization? Well, optimization is a method that is widely used in a lot of decision making context. It is one of the most widely used method in business analytics that can be used to find what is the best course of action or what is the best way to make a decision in a given context. Think about financial planners who have to decide what is the best way to allocate a given amount of money to different types of stocks and bonds given the returns, and the risk associated with them. What is the best or the most optimal way of allocating that money? That's a question you face in financial engineering. Then in the context of human resource managers, you may be interested in asking what is the best way to, schedule my staff, so that I can meet the demand needs from customers. For example, in a call center, then you have to decide how many active duty call center employers need to be present in order to respond to the given call volumes at any time of the day. So there are staffing decisions that you might might need to make and the question is what is the best way to figure out what is the number of employees that I should have at different times of the day? Similarly, you can be asked to figure out what is the best number of employees that I should hire or fire given the future needs of the company. So these are all questions where you're trying to find out what is the optimal number for a particular decision. In the context of airlines, for example, they are interested in selling as many tickets as they can in order to get the highest return or the highest profits while given the constraints of capacity available on a flight. And so they have to decide what is the best way to price them tickets in different classes in order to maximize their profit in the context of manufacturing. Manufacturers need to decide what is the best number of units that I need to even use of a product that I need to manufacture, given the projected demand from customers. In the context of supply chain, you maybe asking questions like how many units of different types of products should I stock as inventory in my ware house in order to meet the future demands? So the fundamental thing that is common across all these different examples from different domains is that the managers have to decide what is the best course of action. What is the optimal number of some things that they need to store or stock, or hire, or invest. Every problem that we looked at has that fundamental thing in common which is using some method to figure out what's the best course of action, what is the optimal decision that I need to make in order to maximise things like profit or minimize things like cost. So as you can see, optimization is that branch of analytics that is widely used in order to find these type of solutions to the decision problems that managers face. And that's why we are going to be looking at linear optimization for decision making in these courses. Now to give you some idea of where this sits in the broader area of business analytics, let me show you the model that we use, the conceptual framework that we use for our students at the cost of school. So analytics as you know is a very large subject area. In order to conceptually understand it, we refer to what is known as the house of analytics model for students to be able to understand where they are or what are they learning which component of analytics are they learning. So let me use that to position this course. So at the foundation of any analytics project is data engineering. You need to clean up your data set. You need to figure out what are the different sources of data that you can tap into, retrieve them from the right databases. Clean them up and then have a clean data to start your analysis with, and then you can do different types of analysis. These are different branches of analytics. You have descriptive analytics where you are looking at the data and trying to figure out what happened or what went wrong, or interesting patterns in the data. Then there is predictive analytics which you saw in the other course, in this specialization where the question is what will happen next? So given the data and the given the past the historical trend can we the future. Ndure. Looking at questions Can we predict the future demand from customers or the future availability off raw materials? Then you have another pillar off analytics, which is causal influence, where you are really interested in figuring out did some factor X caused the outcome? Why on you're trying to understand whether the relationship exists? That's causal influence your causally. Establishing that relation on the last pillar is what we're looking at, which is prescriptive analytics. The question that we ask here is, how should we proceed? So given the data that we have from for a particular context, what should we do? What should we do next? What is the best thing we can do? How should we proceed on? That's where linear optimization comes in as a method which can help you figure out that given this data for a particular contact, what should I do? What is the best course of action? And that's the method off optimization. Finding the optimal solution for your problem and prescriptive analytics really built upon these other pillars that we talked about. For example, in predictive analytics, you could be using the historical data to forecast the future demand from customers in the next quarter. Or you could be using it to predict Theophilus Bility off raw materials in the next quarter. Similarly, you could be predicting how many employees you would have in the next planning cycle. So those numbers by using predictive analytics, you can come up with those numbers. And then once you have those numbers, then the question is, what should I do with those numbers? What is my solution on? That's where linear optimization, prescriptive analytics I'm saying to play, too. Use this method to figure out what is the optimal thing to do in the context, given the numbers that I have. So that's what we're going to focus on in this coast. This is a branch off analytics called Prescriptive Analytics. So optimization problema methods that we're going to learn is sitting right in this column in this prescriptive Analytics column. So with that in mind, let's look at what are learning objectives from this course. So we want to understand how to make a model based that is an analytical, model based, data based analytics approach to decision making. So instead off trying to just look at intuitive solution we are interested in figure out figuring out that, given the data, what is the best or the optimal thing that we can do? And we're going to use this analytical methodology in order to come up with those solutions. So we're going to prescribe, and that's why it's called Prescriptive Analytics. We're going to prescribe the best strategy in a given scenario, given the numbers, and you should be able to formulate this as a mathematical problem. You should be able to understand thes type of problems as to how they're being solved on be able to solve them, using some tools for basic optimization problem. So in this course, you're going to learn how to formulate how to intuitively understand what's going on in terms of the solution on. Then be able to use some tools, which is an excel based tool in this case, to figure out the right solution so that you can go to your workplace on use the numbers. Random said. This problem up in using the mathematical method that we're going to talk about this optimization, solve it using Excel on, then be able to go back into your managers or your colleagues on present that this is the best thing to do. This is the optimal solution that we have for this problem. So we're going to take that approach towards decision making. So in terms of the structure for this course, we're going thio cover the basic components onder Some examples off how to formulate optimization problems in Module one in Model to We're going to look at the intuitive graphical methods that are used to solve simple linear programming problems that is optimization problems. And in Model three, we're going to look at the impact off changes to model parameters on looking at some special cases on finally model for we're going to solve some of the problems that we way we set up mathematically in the previous models were going to be able to figure out how to solve those using Excel solver. So after taking this course, you should be able to formulate simple, linear optimization problems for for a relatively simple context, solve it on, see what the optimal solution Is going to be for that context. In the follow course, the advanced course on optimization, you are going to get more hands on experience with many of these domains that we talked about supply chain finance, manufacturing, human resources, you're going to look at a variety of problems from those domains, and then be able to figure out how to apply optimization in those domains in the next course. So, for the introductory course we're first going to learn what are the basics, how to go about formulating it, what are some of the graphical methods that we can use to solve these problems for simple problems. And then we are going to look at how to use Excel to solve optimization problems and find out the best strategy of the optimal solution for a given context. So that's your structure for this course, and then it will followed up by a more advanced course with more hands-on experience and examples from different domains. So good luck with your course. And I hope you are able to master these skills very fast and you get an exposure to what prescriptive analytics is all about. Thank you for taking this course and welcome to the class.