Analytics involves extensive use of data, statistical analysis, predictive modeling, and fact-based organisational culture to drive decisions and actions. Why analytics? Currently, companies competing in the same industry offer similar kind of products and use comparable technology. High performance business processes are thus the only places where companies can differentiate. Many of the previous bases of differentiation are no longer available. The advantage of unique geographical location no longer matters greatly given the global competition and protective regulations are no longer that strong a deterrent. Proprietary technologies can be copied in no time and breakthrough innovation in products, processes or services is becoming more difficult with the passage of time. What is left as the only basis of competition is constant improvement of business processes and making the right business decisions in shortest time possible. Analytics help the organizations greatly in the pursuit of efficiency and effectiveness of their processes.
What are the business processes where analytics can help? Analytics can support almost any business process. To name a few, customer-based processes like customer segmentation, customer acquisition, customer retention, dynamic pricing, supplier-facing processes like capacity planning and demand-supply matching, financial processes like selecting portfolio of products, credit card scoring and future value analysis, and finally, human resource processes like recruiting and nurturing talents, and selecting and managing vendors.
In its current state, the subject of analytics is crossdisciplinary with inputs coming from the subjects of statistics, computing and management. This programme will provide participants with an overview of the concepts and advanced techniques that are currently being used in business as well as give a glimpse of some techniques that have high potential for use in the near future. The sessions will be application oriented with case studies and hands-on sessions to make the participants get a feel of the techniques.
The programme will be delivered in a Live Online format over the Zoom platform.
For more information or any questions, contact Suman Verma: email@example.com | +91 92277 93191
The following modules will be covered (but will not be limited to) in the programme:
A. Exploratory Data Analysis
In this module we examine how to draw insights from data using simple tools. We also examine how to identify outliers in data and ways to deal with them.
B. Data Visualisation
In this module we learn different techniques of visualising data that can aid in taking effective management decisions.
C. Supervised Learning
This module discusses several methods of supervised learning namely Regression Analysis (Linear and Logistic), Decision Trees, Random Forests and Support Vector Machines. The advantages and disadvantages of these widely used methods for management decision making are discussed with several case studies.
D. Unsupervised Learning
This module discusses unsupervised learning techniques such as Clustering, Dimensionality Reduction and Anomaly detection with applications to management domain through case studies.
This module discusses several techniques that can be used in different situations for forecasting the quantities of interest in management decision context using case studies.
In this module we discuss optimal decision making in the presence of constraints. The Linear programming method is discussed and its applications to management decision making is highlighted using case studies.
G. Bayesian Data Analysis
In many problem situations managers have some information about the problem under study. Effective use of such information helps in making better decisions. In this module we discuss how Bayesian techniques can lead to better management decision making use of the available prior information.
H. Unstructured Data Analysis
In many situations in real life we deal with data that is not structured. One area of prime interest where we encounter unstructured data is when we have to deal with text data such as when dealing with social media comments data. In this module we discuss text data analysis and its application for making better management decisions.
I. Data Analysis Project
The participants will have to work on a data analysis project as a group and will have to make a presentation on the last day of the programme.
The teaching methodology for this programme will be an appropriate mixture of classroom teaching, hands-on experiments, case discussion, identification of best practices, in-class participation, group reading and presentations, guest lectures and panel discussion.
This programme is intended for enabling practitioners, managers and decision-makers to use advanced analytics for better decision-making and to gain in-depth understanding of these concepts using hands-on technique(s) and by relating to business cases. The programme may also be of interest to participants from various analytics organizations to better understand the underlying concepts of these advanced techniques. An aptitude for quantitative modeling and some prior experience in use of analytics is desirable.