Sales Analytics Part II Predictive Methods

Duration

45h Th

Number of credits

Lecturer

Stéphanie Aerts, Morgane Dumont

Language(s) of instruction

English language

Organisation and examination

Teaching in the first semester, review in January

Schedule

Schedule online

Units courses prerequisite and corequisite

Prerequisite or corequisite units are presented within each program

Learning unit contents

Sales Analytics refers to the practice of generating insights from sales data, trends, and metrics to set goals and predict future sales performance.

In the Sales Analytics I course, a prerequisite for this one, students were introduced to the fundamental concepts of data collection and management, data visualization and dashboarding to summarize complex data sets, as well as to some descriptive techniques used in the field such as association analysis or (semi-)automated segmentation.

In this advanced course, divided into two main complementary parts, students are introduced to predictive and forecasting techniques.

Part I: Predictive Methods - Machine Learning/AI

Artificial intelligence systems allow to analyze and understand the collected sales data, to learn from it and to recommend actions (e.g. pricing strategies, predicting the next best offer, prioritizing opportunities according to their probability of success,...).

The sales manager of tomorrow must therefore understand the fundamentals of these techniques in order to be able to identify the analysis opportunities they allow, to evaluate the feasibility of a data mining project and to follow its implementation, to analyze the results such methods provide and to be able to critique them.

In this course, the fundamental concepts of predictive methods will be discussed. Several classical techniques (decision trees, regression,...) will be introduced and applied to real data sets. The focus will be on understanding the techniques and the interpretation and discussion of the results.

Part II: Sales forecasting

An effective sales forecast enables better decision making, risk reduction, sales quota alignment, better territory coverage and quota planning, the ability to focus a sales team on high revenue, high return sales pipeline opportunities, ... The use of data-driven predictive analytics reduces the impact of subjectivity and provides a solid forecast basis.

In this course, classic sales forecasting techniques will be discussed and applied to various data sets.

Learning outcomes of the learning unit

Part I:
Upon completion of this unit of instruction, the student will be able to:
- Understand and explain the fundamental principles of predictive methods
- Choose the most appropriate AI technique(s) to answer a problem
- Identify the limitations of the AI techniques used, their advantages and disadvantages
- Use an AI tool/module
- Interpret the results of predictive analysis
- Demonstrate critical thinking and analytical skills in monitoring a project using machine learning
 
Part II:
Upon completion of this unit of study, the student will be able to:
- Understand and explain the basic principles of forecasting
- Select the most appropriate forecasting technique(s) for a given data set
- Identify the limitations of the forecasting techniques used, their advantages and disadvantages
- Use a forecasting tool/module
- Interpret forecasts obtained with a forecasting model
- Use critical thinking and analytical skills when dealing with sales forecasts

Prerequisite knowledge and skills

The Sales Analytics I course is a prerequisite.

Planned learning activities and teaching methods

The learning sessions will be of several kinds:

- lectures interspersed with exercises of direct application of the concepts

- practical demonstration on software 

- group work on business cases and Q/R session

Mode of delivery (face to face, distance learning, hybrid learning)

Face-to-face course


Additional information:

Face to face

Course materials and recommended or required readings

All required documents will be posted on lola.

Exam(s) in session

Any session

- In-person

written exam ( multiple-choice questionnaire )

Written work / report


Further information:

The student will be evaluated on the following elements:

• Two case studies with written reports and an oral presentation.
  
  Case study 1: Predictive Methods
  
  Case study 2 :  Forecasting
  
  Oral presentation of the case studies :
  
        1. The group will present the case studies. Each student of the group has to present a part of the work. 
  
        2. Each student of the group will have to answer different individual questions about the case studies

• Examination: written MCQ or short answer type, closed course.

Work placement(s)

Organisational remarks and main changes to the course

All sessions require the use of a laptop with all course software installed.

Contacts

S. Aerts (stephanie.aerts@uliege.be)

M. Dumont (morgane.dumont@uliege.be)

Association of one or more MOOCs