Personal and Professional Reflection: The Employee Attrition Project
In the final component of your capstone, you will write an essay to discuss the process and outcomes of the project, as well as how your coursework culminated in the capstone. You may want to draw on the list of possible actions from the deployment where you identified errors and/or omissions (if any). Also, discuss identified strengths, as well as problems of any other nature (e.g., systems, applications) while completing the project. Finally, in the essay you will discuss how the capstone may be useful in your career endeavors or in furthering your education.
The personal reflection in your capstone is the holistic culmination of your experience in the Data Analytics program. It is similar to a “Lessons Learned” session that takes place on a team after a project completes. In your personal reflection, you will discuss not only what you did, but also what you intended to do. What worked well and what were the challenges you faced? What would you change or approach differently to improve on your experience? Your personal reflection is not about
the capstone, but rather your experience with the capstone project and your reflection of your knowledge, skills and abilities (KSAs).
Your project reflection should include, but is not limited to, the following:
Ethical Considerations:
What ethical considerations did you make or should you have made during your project, and why?
What is the importance of and how can you ensure data integrity, protection, and appropriate use within the context of this project and future projects?
How has your capstone helped you create a framework for practice that promotes ethical approaches to social practices?
Career Connection:
How could you best position your knowledge of data analytics as an advantage in your professional life? Why is this important? What has this project proved about the use of analytics?
How will you apply what you have learned to your future academic and/or professional life?
Professional Practice:
If you were to implement your analytic project/solution in a real company or organization, how would you approach collaborative and project management needs that you might not have had to deal with when developing your own, single project?
Reflect upon the communication, collaboration, cross-functional and diverse teams, and leadership skills and strategies that have developed throughout this project. How will these benefit you in your professional life and what further learning and development do you see for yourself?
Where do you see your own strengths and weaknesses in relation to the outcomes for this capstone experience?
Which of your professional skills (e.g., reading comprehension, critical thinking and analysis, research, writing, communication) have improved the most as a result of your coursework in this program, and why?
Personal Reflection:
What academic connections do you see between your capstone and your academic program?
How has your capstone related to your overall program experience at SNHU?
Overall, how would you characterize your capstone experience from a personal and professional perspective?
Personal and Professional Reflection
Author
Affiliation
Course
Instructor
Due Date
Employee Attrition Project
The project on employee attrition has been a real eye-opener in data analytics. It has changed my perspective on how I view data. The employee attrition project sought to address a real-world problem using a data-driven approach. Companies lose 80 percent of the employee's annual salary when an employee leaves the company prematurely. Because companies spend a significant amount of time and finances training employees, we developed a machine learning model that utilizes a random forest algorithm to predict attrition. The main strengths of the model were its scalability. The model is robust enough to take up a large dataset and can be deployed in a real-world scenario. However, the model's predictive power was limited by insufficient data. The assessment outcome of the model indicated that it was biased in predicting one outcome better than the other. The biasness is attributed to the imbalanced data used during training. The project has been useful in preparing for an actual work environment as a data analyst. The project has helped me become aware of what it takes to be a competent data analyst.
To solve the problem of imbalanced data, I tried adjusting the weights parameters in the model but yielded no fruits. I intend to try a different algorithm and collect more data on employee attrition in the future. The CRISP-DM methodology was valuable as it became the project's true "north star." The CRISP-DM methodology was easy to implement and become a good guild for the successful implementation of the project.
Ethical Considerations
The compelling ethical consideration in this project was the use of personal data provided, which may violate privacy laws (Burgess, 2020). Nevertheless, data encryption could be undertaken to guarantee data protection against privacy violations. However, the dataset had no names of employees while their employee identification numbers had been replaced. The integrity of the dataset was critical since the model's training requires consistent, reliable, complete, accurate, and valid data to produce a compelling model (Lund, 2021). The project has been reso...