ANALYTICS TOOLS FOR BUSINESS - 2021/2

Module Overview

The business world is inundated with data with the difference between a successful business and another is its ability to understand this data. Analytics Tools for Business will first familiarise students with the practical aspects of Artificial Intelligence (AI) and Machine Learning (ML). It will teach the underpinning statistical concepts and elementary programming for non-technical students. The students will learn how to undertake an analytics project using these concepts with the taught analytics software tools. Vendor, semi-commercial and open-source software tools will be introduced and used by students to construct and maintain a robust data workflow, analyse data and turn it into compelling insights to produce business reports. Indicative tools include IBM SPSS Modeller, Microsoft Azure, R language/markdown, Weka, Microsoft Azure and Tableau (in common use within industry). This module is software tools based and requires significant practical support. The teaching is based on real-world datasets, business case studies and industry recognised best practice approaches.

Business Analytics (BA) is about helping business to make evidence-based decisions using data
collected from sources from inside and outside a company. This data is often diverse, complex, inconsistent and needs to be processed, analysed and modelled to gain business insights for decision making. Best practice-based techniques will be used to visualise and create ML models to predict, estimate or classify in real-world examples to aid decision making based on imprecise, real-world sets of data using software tools. The Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology will be used throughout which provides the framework for undertaking a real-world business analytics project using analytics software tools. This includes six key steps: (1) Problem Understanding, (2) Data Understanding, (3) Data Preparation, (4) Modelling, (5) Evaluation, (6) Deployment. The student will learn how to use the range of analytics software tools provided in the labs, within the CRISP-DM framework to create a data pipeline; including data management and analysis, training models to predict, estimate or classify and visualisation for decisions.

Module provider

Surrey Business School

Module Leader

EMROUZNEJAD Ali (SBS)

Number of Credits: 15

ECTS Credits: 7.5

Framework: FHEQ Level 5

Module cap (Maximum number of students): N/A

Module Availability

Semester 2

Prerequisites / Co-requisites

N/A

Module content

The module content will focus on a selected set of critical areas in data analytics and the software tools used. As an indication of the kind of concepts that will be covered, below is an indicative set of topics:

· Ingredients of analytics / key concepts / Taxonomy of algorithms. Types of analytics

· Classification / Clustering / Regression

· Identifying business applications / feasibility / High level design

· Using software tools

· Introduction to R Language

· IBM SPSS Modeller / Weka / etc. and high-level applications

· Linear / Non-Linear regression for Prediction

· Evaluating models & Visualising Performance

· Cross Validation / Measures / Visualising performance

· Project Life-Cycle

· Knowledge Discovery / Analytics / Decision Support

· Preparing data

· Decision Tree (ID3), Top Down / Entropy / Random Forest

· Shallow MLP & Deep Neural Networks

· Specifying the training algorithm / Gradient Descent

· Evaluating classifier performance

· Unsupervised learning / Hierarchical Cluster Analysis / Partitional / K-means / Choosing k

· Neural Network / Competitive Learning / Self-Organising Map

· Association Rule Mining / apriori algorithm

· Visualisation / The four pillars to inform

· Human perception / Design Choices / Getting it right

· Infographics / Dashboards

Assessment pattern

Alternative Assessment

An alternative to the group project is a defined individual project using a given dataset and problem description (1500 words for the individual).

Assessment Strategy

The assessment strategy is designed to provide students with the opportunity to demonstrate:

· Knowledge of the entire data analytics workflow process

· Appreciation of the objectives for robust data analytics workflow processes

· Ability to apply the theories, conceptual frameworks and methodologies that underpin data analytics in common software tools and languages

Thus, the summative assessment for this module consists of:

· Analytics Tools Group coursework 3000 words (60%)
For the project coursework, the students will work either individually or in small groups, to apply and deepen their knowledge with the criteria related to learning outcomes (1) to (5). The project will include the analysis of a set of real-world data using data analytics techniques within the taught software tools and visualising the results appropriately to produce a written report. Evidence of background reading must be provided. the project provides an opportunity for the student to experience the whole process of data analytics using machine learning by using the taught software tools using the approaches introduced in the labs, to undertake all necessary steps using the CRISP-DM methodology. The student will present the project findings and conclusions in a written report, give an oral presentation and provide code used, all of which will be marked. Students will be informed about the coursework topic and individual/group at the beginning of the semester.

· Analytics Tools examination (40%)
The 2-hour examination will be a standard closed book examination, with material coming directly from the module content. The broader topics for the questions will be covered during the taught and laboratory sessions. The problems will be similar to those discussed in the taught component, computer laboratory or indicated in the essential reading material. The answers will mainly be discursive and will be in alignment with the criteria related to learning outcomes.

 

Formative assessment

· Online assessments tied to lab sessions

 

Feedback

· Group feedback on lab session results – common errors, examples of good practice.

· Individual feedback after online assessment covering key concepts.

Module aims

• · Introduce students to the practical elements of the data workflow (e.g. data management,
  
  data analysis) that turn diverse data sources into useful insights for decision-making.
• · Teach students how to conduct key exercises along the data workflow process (e.g. how to clean data, how to visualise data).
• · Introduce software tools that can be used for each part of the data workflow process (e.g. R for data analysis, Tableau for creating data dashboards).

Learning outcomes

Methods of Teaching / Learning

The learning and teaching strategy is designed to:

· encourage a critical understanding of the importance of a robust data workflow that translate diverse, often messy data sources into useful insights for decision-making.

· cultivate an understanding of the main issues and challenges; provide a coherent conceptual framework; develop a critical awareness of the various approaches of machine learning.

· introduce students the concept of a robust data workflow and to teach the basics of the various tools that enable operational delivery of data insights in business. The intention is to teach the objectives of the data workflow process (e.g. clean data, simple to understand insights) and how that relates to the decisions to be made off the data, rather than an exhaustive list of prospective software.

 

The course will be practical, encouraging students to get hands-on with example data analytics software tools that allow them to progress through all stages of the data workflow process, giving them an appreciation of the operational processes and software required to deliver effective operational data processes in business.

Indicated Lecture Hours (which may also include seminars, tutorials, workshops and other contact time) are approximate and may include in-class tests where one or more of these are an assessment on the module. In-class tests are scheduled/organised separately to taught content and will be published on to student personal timetables, where they apply to taken modules, as soon as they are finalised by central administration. This will usually be after the initial publication of the teaching timetable for the relevant semester.

Reading list

https://readinglists.surrey.ac.uk
Upon accessing the reading list, please search for the module using the module code: MAN2189

Other information

N/A

Programmes this module appears in

Please note that the information detailed within this record is accurate at the time of publishing and may be subject to change. This record contains information for the most up to date version of the programme / module for the 2021/2 academic year.