讲解 Business Analytics (MIS3003S)讲解 R编程

Business Analytics (MIS3003S)

WELCOME MESSAGE

As co-ordinator of the Business Analytics module, I wish to welcome you to the module. To operate effectively within the Global Business World, an understanding of the theory and practice of Business Analytics is essential. This module is designed to deepen your interest and expertise in the area of Business Analytics and the Study Guide is designed to support your learning. While much of the focus is on knowledge acquisition, attention is also given to enhancing and developing your professional and personal skills and competencies. To successfully complete this module, several learning activities are to be completed, which should facilitate the attainment of the module learning outcomes.

In recent years, especially with the advent of high-performance computing, analytical and mathematical approaches have become increasingly important in addressing business, engineering and other problems; notably problems where a decision must be made subject to constraints such as limitations on resources, or data analytics problems where we seek useful information in a large dataset.

Business analytics is the field of study concerned with quantitative methods of analysis in the context of business. Business analytics means using data, mathematical modelling, statistics, and computer techniques to achieve these goals in the context of business: understanding, prediction, and decision-making.

In this module we focus on linear and non-linear modelling, and optimisation techniques. The objective of this course is to develop an understanding of the application of quantitative analytical techniques for problem solving in business and management. Participants will learn how to conceptualise complex business problems and transform. them into a set of equations (models) that describe the problem. For example a regression model, when we are given several data samples (such as transactions) and generate a corresponding mathematical equation, may be used to understand the relationship between the driving variables behind the response, predict response values for unseen scenarios, and make decisions to optimise business profit as a result.

We emphasise how to correctly formulate a mathematical model (given a real-world problem description), and the trade-offs necessary between comprehensiveness and usability. Once modelled, the problems can be solved using optimisation techniques such as Linear Regression or Linear Programming.

Participants will be introduced to the use of computer packages to implement models for sample problems and assignments. The principles of Active Learning guide the face-to-face contact sessions with students engaging in hands-on mathematical modelling exercises.

PART 1: INTRODUCTION

This Study Guide is designed to provide you with details of this module, the learning outcomes, delivery and assessment arrangements. The Study Guide consists of 6 parts.

Part 1 provides background details to the subject area and the broad aims of the module are set out.

Part 2 consists of the module outline. In this part (a) the module learning outcomes, (b) the themes and topics to be explored and (c) the learning supports to be used are explained.

Part 3 gives details of the module delivery arrangements. It sets out the session arrangements and the expectations in relation to your prior preparation and student engagement.

Part 4 provides details of the assessment techniques used in this module explaining the assessment components and their rationale.

Part 5 explains the UCD grading policy and grade descriptors drawing on the university document for each assessment component (i) Assignment 1, (ii) Assignment 2 and (iii) Examination (closed book).

Part 6 presents the concluding comments.

Brightspace Contents

This module will be delivered using face-to-face lectures, with online introduction and conclusion sessions, via UCD’s Brightspace platform. It will consist of a series of chapters. All the contents related to each chapter will be made available through the corresponding Brightspace module page.

You will find all the relevant materials under “My Learning” -> “Learning Materials”. Each chapter will have the following documents available to you:

· Chapter Notes. This is a single PDF document, with detailed notes related to this chapter. The notes go into much detail, to ensure your understanding of the materials. They have been specifically designed for this course delivery.

· Video Lecture. A pre-recorded video lecture, going through the chapter materials. The video lecture follows the notes structure carefully. It explains the concepts in a simple to understand way, going through a slide deck with the lecturer’s voice-over. When required, use of Microsoft Excel and/or other software will be made, to further enhance your understanding.

· Slides. A PDF document containing the slides used during the video lecture. These are a compact version of the chapter notes, and are also great later on to recall the concepts learned.

· Support Documents. Usually each of the chapters goes through an example scenario, where you learn how to apply an analytics technique. The data files (usually Excel files) related to this, which are used during the video lectures, will be made available.

· Practical Excel Implementation Video. The Video Lecture mentioned above carefully goes through the theory of the chapter, and only briefly mentions/exemplifies how to implement it in Excel. As such, one or two tutorial videos go through the Excel implementation of the techniques of the chapter in a lot of detail, to ensure your full understanding.

· Practical Exercise Sheet. For each chapter, a practical exercise sheet is available. This is a single PDF document, with either theoretical or practical (Excel) exercises to test your understanding of the materials.

· Practical Exercise Support Documents. When required, a set of document related to the exercise are made available (e.g. Excel files).

· Exercise Solution. For each exercise sheet, a detailed set of solutions is available. This is usually a PDF document, but may also be an Excel document with the implementation of the exercises.

Although the above documents have been carefully designed to ensure your understanding, it is normal to have questions/doubts after the delivery. As such, I will be contactable through e-mail, and will answer any query within at most 48h (usually much less).

Background Details

Mathematical Programming and other mathematical modelling techniques have long been used in business to model and solve business problems. In recent years, especially with the advent of high-performance computing, mathematical approaches have become increasingly important in addressing business, engineering and other problems; notably decision problems where a decision must be made subject to constraints such as limitations on resources. In the last decade, the discipline of Analytics (incorporating Management Science and Operations Research) has arisen, where mathematical, statistical and computational techniques are used to aid decision making by extracting the crucial information from large datasets. Analytics covers everything from the soft science of multi-criteria decision making to exact approaches used by numerical methods and optimization techniques.

Recent surveys by Accenture, IBM and others have shown:

· 83 percent of respondents identified business analytics as a top priority and a way to enhance competitiveness;

· 72 percent are working to increase their company’s analytics usage;

· only half believe they are spending enough on analytics;

· over a third said they face a shortage of analytical talent.

This course introduces the concept of Mathematical Modelling in Management Decision Problems, and surveys some of the major mathematical models used in such approaches. It concentrates on methods such as Linear Regression, Linear Programming (LP) and its relatives, classification, and clustering.

We emphasise how to correctly formulate a model (given a real-world problem description), and the trade-offs necessary between comprehensiveness and usability. You will be introduced to the use of computer packages in working out examples and assignments.

Our course will have a practical element, so we will learn to solve problems both on paper and by using computer software.

Module Aims

The aim of this module is to provide students with an overview of the theory and practice of a range of Mathematical Modelling approaches in Management Decision Problems. This includes:

· Describing the main principles of a suite of key regression, linear programming, classification, clustering, and other mathematical modelling approaches as they apply to decision problems and optimisation;

· Application of these principles to improve the quality of analysis and decision-making;

· Discussion of a portfolio of important business and other applications of these principles;

· Understanding the use of mathematical computer packages and information technology as an aid in decision making.

These are fleshed out in the themes below. The assessment tasks for this module have been designed with this in mind as detailed later in the study guide.

Programme Goals