Sales Representative Net Promoter Score Analysis

Project Summary

The Sales Representative Net Promoter Score Analysis project aims to identify the key drivers of a high Net Promoter Score (NPS) among college-educated employees in the software product group. The goal is to create a classification model that can effectively predict whether a sales representative will receive an NPS score of 9 or higher. The analysis explores the impact of various factors such as demographics, qualifications, salary, feedback, and certifications on NPS scores. The findings provide insights to help businesses optimize customer satisfaction and loyalty. 📈💼

Project Findings

The analysis reveals several key findings:

• Personality traits, specifically "diplomat" and "explorer," have a higher likelihood of achieving an NPS score greater than 9, while "analyst" and "sentinel" personality types have a lower chance. 😃🔎
• Experienced sales representatives tend to have higher NPS scores compared to entry-level and mid-level counterparts. 📊🏢
• Sales representatives with higher salaries and more certifications have higher NPS scores, indicating the importance of experience, expertise, and motivation. 💰📚
• Feedback plays a significant role, with sales representatives receiving excellent positive feedback having a higher chance of achieving NPS scores greater than 9. 📝👏

Recommendations

Based on the analysis, the following recommendations are made to improve NPS scores among technical sales representatives:

1. Identify and recruit sales representatives with personality traits that align with different sales roles, giving preference to those with "diplomat" and "explorer" traits. 🕵️‍♀️🤝
2. Offer competitive salaries to sales representatives to keep them motivated and improve job satisfaction and motivation, leading to higher NPS scores. 💼💪
3. Invest in the training and development of sales representatives, particularly in improving their skills and knowledge to enhance their performance. 📚👩‍🎓
4. Prioritize representatives with excellent positive feedback, as they are more likely to achieve NPS scores greater than 9. 👍🗣️
5. Encourage sales representatives to obtain certifications, as it increases their credibility and perceived expertise, resulting in higher customer trust and loyalty. 📜🏆

Implementing these recommendations can lead to higher NPS scores, ultimately improving customer satisfaction, increasing sales, and driving overall business success. 💯📈

Files in the Repo

• Advanced_Model_Stacking - (Selected model).R: R script for the advanced model using stacking technique.
• Advanced model (stacking): File related to the advanced model with stacking.
• Executive Summary (Sales).pdf: Report summarizing the findings and analysis of the project.
• Logistic_Regression_Model(Sales).R: R script for the logistic regression model.
• Other models (DT + NB) (Sales).zip: Compressed file containing other models using decision tree and naive Bayes.
• README.md: Updated README file providing an overview of the project, its findings, recommendations, and other relevant information.
• Sales Dashboard PDF.pdf: Tableau Dashboard showcasing sales analysis results in a PDF format.
• Sales Data Analysis.xlsx: Excel file containing pivot tables for additional data analysis.
• Sales_Dashboard.twb: Tableau file for the sales dashboard.

Technologies Used

The project utilizes the following technologies and tools:

• R: Programming language used for statistical analysis and model building. 📊📉
• Python: Programming language used for data manipulation and analysis
• Tableau: Data visualization tool used to create interactive dashboards and reports.
• Excel: Spreadsheet software used for additional data analysis and pivot tables.

Please refer to the data_analysis.R script, Sales Dashboard PDF.pdf, and Sales Data Analysis.xlsx for detailed analysis and visualizations.

For any further information, please contact me at jj5603@rit.edu.