Faculty: Amit Kumar

---

Domain Track Title :Business Analytics

Track Total Credits BACU2210 (0-13-7)

Courses Division( list all divisions):

1. (Code:CUBA2210) :Marketing Analytics                                   (0-2-1)
2. (Code:CUBA2212) :Financial Analytics                                     (0-2-1)
3. (Code:CUBA2213) :Agriculture Analytics                                 (0-2-1)
4. (Code:CUBA2214) :HR Analytics                                              (0-2-1)
5. (Code:CUDA2201): Basic of Python: Numpy and Pandas        (0-2-1)
6. (Code: CUDA2202):Visualization with Matplotlib, Plotly and Seaborn (0-1-1)
7. (Code:CUBA2211): Business analytics through Excel             (0-2-1)

Domain Track Objectives:

To understand and apply data analytics tool in different business and agriculture domain

Domain Track Learning Outcomes:

1. Students can apply data analytics tool in different domain
2. Students will be able to make inferences using different analytics tools.

Domain Syllabus:

• Marketing Analytics (2-0-1)

  
 
Module: I
 

• Overview of the marketing process,
• Transformational role of analytics in marketing,
• Metrics for Measuring Brand Assets,
• Customer Lifetime Value (Major emphasis on B2C).

 
Module: II
 
2.1 Market Segmentation, segmentation variables,
2.2 Segmentation techniques using cross-tabulation,
2.3 Regression, clustering, and conjoint-analysis (Major emphasis on B2C).
 
Module: III
3.1 Marketing experiments (like price cut vs sales, advertising effectiveness etc with respect to B2C),
3.2 Sales Forecasting, sales forecasting methods including moving average, exponential smoothing, and regression.
 
Project/Case Studies
 
Sales Forecasting and marketing experiments of UMBC shall be a good one for the students to get the exposure. The students shall be divided into several groups according to the product lines of UMBC. Each group shall get the past sales data of the UMBC product lines and using those they have to use the sales forecasting methods to estimate the future. This project data can be used to develop an original case study on UMBC based on the output of the project.
                                      

• Finance Analytics (2-0-1)

 
Module I
 
2.1 Quick introduction to Python
2.2 Understanding data in finance, sources of data
2.3 Cleaning and pre-processing financial data
2.4 Exploratory Data Analysis in Finance
 
Module II

• Building Models using Accounting Data
• Understanding stock price behaviour, time series analysis in finance

Module III

• Forecasting stock prices
• Credit risk modelling

 
 
Case studies/Project -

• Security Assessment

A framework can be defined as a supporting structure to an entity, which in this case is the investment option. We extend this definition of a framework through a visualization approach that supports a range of key data points of each listed security. First, we introduce and define how that framework is designed; second, we apply it to the creation of profiles for stocks, bonds, mutual funds, and ETFs; and third, we present the resulting collection of profiles. Throughout this chapter we show how the framework is constructed with blueprints for each security type.

• Portfolio Construction

This Project presents a variety of Portfolio Construction data visualizations that draw from activities top-down managers employ. These activities include determining asset allocations with sector and industry weights before security selection represented with visualizations that show current and proposed asset allocations of a portfolio, sector leadership, and sector alpha factors. In addition, two common risk management techniques, overlap of holdings and stress tests, are included as indirect inputs toward Portfolio Construction activities. These types of techniques manage firm risk from a business perspective to influence Portfolio Construction decisions. They also present clients with rationale for amendments and changes in their portfolio(s).
 

• Showcasing Data for Effective Communications

This Project reuses the Waterfall chart and introduces the Cascade chart to represent cash flows data for for-profit organizations. Like variations on a theme, this section shows how to apply the Cascade chart technique to a variety of use cases. From Waterfall to Cascade, Summary to Detail, Single to Multi-year, each variation is tailored to serve different needs.
Financial statements are known for accuracy and attention to detail and employ a uniform method to gather and present data. The examples in this chapter maintain conventional standards of financial statements while introducing visuals to augment the standard tables. The visualizations reflect the direct and accurate stance of financial statements with the use of straight lines to indicate Summary 213 precise aggregate levels, negative and positive flows, and quantity changes across the years.

• Visualizations of Performance

This project discusses the redesign of core component visualizations and shows how to integrate them within qualitative information and quantitative tables. The Fund Fact Sheet, for example, combines these redesigned visual components with textual description to convey qualitative information. In contrast, the quantitative table shown in the “Mutual Fund Comparison” section provides a column of visualizations next to corresponding numeric values to compare a short list of funds. In the former case, visualizations vary and represent different data sets with comparison points within the fund. In the latter, the visualizations are consistent and repeat for comparison across a list of funds. Both use cases produce a diverse set of mutual fund data visualizations.
 
 

• Agriculture Analytics (2-0-1)

 
 

Module-1
Basic Statistics review,
Review of descriptive statistics,
Interpretation and visualization of agricultural data
 

Module-2
Inferential statistics involves generating, from a limited data set, Information about statistical relationships and estimates about a population.
Hypothesis testing and ANOVA, Design of experiments.
 

Module-3
Simple linear regression,
Multiple regression,
Time series analysis,
Growth and instability study in crop productivity,
Response surface methodology for input output optimization.
 
Case study-
 
Statistical analysis on price index of different agricultural commodities -
Description:
A price index is a normalized average (typically a weighted average) of price relatives for a given class of goods or  services in a given region, during a given interval of time. Price indices have several potential uses. For particularly broad indices, the index can be said to measure the economy's general price level or a cost of living. More narrow price indices can help producers with business plans and pricing. Sometimes, they can be useful in helping to guide investment.
Study under coverage-
Consumer price index, producer price index, export and import price index for agriculture commodities.
Agriculture crop production modeling and forecasting
Description:
Modeling and forecasting of agricultural crop production is essential for policy maker and researcher to predict the future behavior of production or productivity.
 
Study under coverage –
Different crop modeling and forecasting for area, production, productivity
 

• Hr Analytics (2-0-1)

 
Module: I
Human Resource planning: Forecasting demand and supply, HRIS, succession planning; job analysis: job description & job specification; Recruitment and Selection: Sources of recruitment (internal & external), E- recruitment, Selection Process; Orientation Process; Human Resource Development: Concept and challenges.
Module: II
Training and Development: Concept, needs, methods and effectiveness; Career Planning: Career anchor and career life stages; Promotion: Purpose, Types of promotion; Performance Management System: concepts, use, methods, common problems of rating; Compensation: job evaluation, components of pay structure, factors influencing compensation levels, wage differentials & incentives, profit sharing, gain sharing, employees’ stock option plans, fringe benefits
 
 
 
Case study
Ibm Hr Analytics Employee Attrition Modeling - Pandas
 

• Basic of Python: Numpy and Pandas (0-2-1)

Modules

• Inbuilt function of Python
• Numpy one and two dimensional arrays
• Understanding series and dataframe in Pandas
• Data operation in Pandas
• Pandas Sql Operation

Case study
Working with project on Numpy one and two dimension arrays
Analysis of Newyork City Fire Department Dataset – Pandas

• Data Visualization in Python using matplotlib and seaborn (0-1-1)

 
Module

• Line properties
• (x,y) Plot and Subplots
• Types of Plots

 
Case study -
Population immigration analysis for last 50 years – Matplotlib and Seaborn
 

• Business analytics through Excel (0-2-1)

Module

• Exploring Data
• Data Wrangling
• Analyzing Data
• Decision Making

Case study –
Preparation of sales Dashboard and Business Interpretation

Session Plan for the Entire Domain:

List of Projects/ papers/jobs/products to be done in domain: