Client Proposal
Document Information
| Document Title | Salifort Motors - Client Proposal |
| Author | Rod Slater |
| Version | 1.0 |
| Created | 01-11-2023 |
| Modified | 16-11-2023 |
Client Details
| Client Name | Salifort Motors |
| Client Contact | Mr HR Team |
| Client Email | hr@salifortmotors.it |
| Client Project | HR Team Data Driven Solutions from Machine Learning Models |
Capstone project: Providing data-driven suggestions for HR
Client Proposal Document Client Proposal Presentation (Libre Office)
PLANNING
Timeline
Planning Tasks
Identify Stakeholders and build Communications Matrix, Stakeholder Analysis
Stakeholder Meetings
- Discuss and agree with stakeholders:
- Project objectives
- Project Deliverables
- Project Timescales
- What does success look like?
- limitations of machine learning
Data Tasks
- Collect & Review Data Sources
- Identify tools and models (multi model approach to identify best fit)
Analyse Data
Analyse - Tasks
- Ethics Review (transparency, accountability, fairness, privacy, security, consent, and integrity.)
- Perform Exploratory Data Analysis
- Develop descriptive variable statistics & identify any trends
Analyse - Deliverables
Jupyter Notebooks
Construct
Construct Tasks
- Define dependant and independent variables
- Build ML Models for logistical Regression, Decision Tree, Random Forest and XGBoost
- Record model performance
- Evaluate model performance choose best performing model
Deliverables
- Demonstration ML Model
- Model Risk Predictions on Live HR Data
- Model Comparisons#ML Driven mitigation cost analysis
Execute
Execute - Tasks
Interpret Results Create Summary of the analysis Define limitations and what can be done to improve the models (more data)
Execute - Deliverables
Client Documentation
Summaries
- EDA Analyst's Report
- HR Report
- Executive Summary
Jupyter Notebooks :
- EDA
- Different ML Models
- Model performance comparisons
- ML Model Demonstration
- Team Report generator
Executive Summary
- Executive Summary
- Recommendations
HR Summary
- Report by team on current employees
LeavePredictions on current employees- Interactive Demonstration ML Model
- Predictions datafile on current employees
Analyst's Summary
- Clear and Concise summary of the analysis
- Outcomes
- S.M.A.R.T Proposals
- Further Research ideas
- Working ML Model to apply to current employee Data