The Data Science Lifecycle is an iterative approach to managing data(cleaning, processing, contribution,…) and data analysis.

1. Business Understanding & Prioritization
2. data acquisition, mining & ingestion
   • Data discovery & collection
     • Datasets and Databases, API. I.e. CSV, Data-frames, Parquet files, etc.
     • Web Scrapping
     • Survey data
   • Data integration
   • Data fusion
   • Transformation & enrichment
3. data exploration: Exploratory Data Analysis (EDA)
4. data cleaning
   • Data scrubbing
   • Handling Missing Values
   • Unbiased estimators
   • De-noising
5. Data Analysis
   • Analyze data
   • Feature selection
   • Feature engineering
   • Model selection
6. Data modeling
   1. Model creation & parameter tuning
   2. Model Evaluation & Bias Check
   3. Model Deployment
7. Report and Delivery: Communicate actionable insights to key stakeholders.
   • Presentation of findings
   • Data visualization
   • Credibility counts: check if your research is valid

~ Business Level Action:

• Act by using insights
• Measure impact of action
• Goal orientation and realignment