Internship Report on Data Science Internship at DevSkillHub Shivam Kumar 2024
Declaration I, Shivam Kumar, declare that the work presented in this report is entirely my own and has not been copied or reproduced from any other source.
Internship Certificate This is to certify that Shivam Kumar completed a Data Science internship at DevSkillHub from 28th May 2024 to 29th July 2024, under the supervision of Mr. Vamshi Krishna.
Acknowledgment I would like to express my sincere gratitude to my supervisor, Mr. Vamshi Krishna, and the entire team at DevSkillHub for their support and guidance throughout my internship.
Certificate by Examiner This is to certify that the internship report submitted by Shivam Kumar has been examined and approved by the examiner.
Abstract This internship report outlines my learning experience at DevSkillHub, focusing on data preprocessing, model building, and customer churn prediction using Python. The report covers objectives, tasks, challenges, and outcomes of the internship.
List of Tables Table 1: Customer Churn Model Performance Table 2: Data Preprocessing Steps
List of Figures Figure 1: Data Distribution Figure 2: Model Accuracy Comparison
Abbreviations EDA: Exploratory Data Analysis SMOTE: Synthetic Minority Over-sampling Technique
Chapter 1: Internship Overview This chapter provides an overview of the internship, including objectives, company details, and the intern's role.
Chapter 2: Data Science Concepts This chapter explains key concepts such as data preprocessing, exploratory data analysis, and feature engineering.
Chapter 3: Machine Learning Development This chapter covers the development of machine learning models for customer churn prediction, including data cleaning, model training, and evaluation.
Chapter 4: Project Outcomes This chapter discusses the outcomes of the project, highlighting the model's performance and future improvements.
Conclusion and Future Scope In conclusion, the internship provided valuable experience in Data Science. The future scope of this project includes further model optimization and deployment for business use.