Case Study – Improving Business-to-Business Sales Using Machine Learning Algorithms


Case Summary: Champo Carpets is one of the largest carpet manufacturing companies based in India, with customers across the world, including some of the most reputed stores and catalog companies. Champo Carpets is based out of Bhadohi, Uttar Pradesh, which is one of the most famous clusters of carpet weaving in India. This cluster is spread over 1,000 sq. km and comprises many villages and districts in and around it. The company is a vertically integrated manufacturer and exporter of carpets and floor coverings, with more than 52 years of existence. At the beginning of 2020, the company employed 1,500 people with a capacity to produce 200,000 pieces of carpets and floor coverings per month. As part of sales and marketing, Champo Carpets shared sample designs with its potential customers, based on which the customer placed an order. The sample design selection was done in various ways and the process itself is costly and elaborate. To capture industry trends, a team of the company visited various trade shows and events and sent samples to the client as per the latest fiber and color trends. However, their sample-to-order conversion ratio was low compared to the industry average. This had cost repercussions as well as lost opportunities. The company identified the cause as inaccurate targeting of products to their customers. It subsequently implemented an enterprise resource planning (ERP) application and has been capturing data at every point of production as well as sales. They believe this accumulated data can help target their products accurately to the right clients and design an appropriate recommender system.

Learning Objectives The primary objective of the case is to illustrate how machine learning algorithms can be used to manage business-to-business (B2B) sales. The learning objectives include the following:

Access attached the full case or article. After a critical review of the case, respond to the questions below.

For a better understanding of the issues related to the problem, knowledge of data visualization using Tableau, R, or Python programming will be useful.
1. With the help of data visualization, provide key insights using exploratory data analysis.
2. What kind of analytics and machine learning algorithms can be used by Champo Carpets to solve their problems and in general, for value creation?
3. Develop ML models to help identify features that contribute toward conversion (or non-conversion) of samples sent to customers.
4. Discuss the data strategy for building customer segmentation using clustering. What are the benefits Champo Carpets can expect from clustering?
5. Discuss clustering algorithms that can be used for segmenting Champo Carpets’ customers.6. Develop customer segmentation using K-means clustering. Discuss the optimal number of clusters, significant variables, and cluster characteristics.
7. Discuss the data strategy that can be used for building recommender system models.
8. Develop an association rule mining algorithm, which can be used for recommendation.
9. Build collaborative filtering techniques for recommender systems.
10. What will be your final recommendations to Champo Carpets?

Requirements:

  • Your analysis will be considered complete, if it addresses each of the 9 components and subcomponents outlined above.
  • Use of proper APA formatting and citations. Supporting evidence from outside resources should be used and those must be properly cited. 
  • Include your best critical thinking and analysis to arrive at your justification.
  • Approach the assignment from the perspective of the senior executive leadership of the company.

    Answer all questions thoroughly. Min 7-8 pages without reference page and main header page.