addition of unit 1 3 4 5
This commit is contained in:
24
unit 1/02_Data_Mining_Process.md
Normal file
24
unit 1/02_Data_Mining_Process.md
Normal file
@@ -0,0 +1,24 @@
|
||||
# The Data Mining Process
|
||||
|
||||
How do we actually do data mining? It follows a standard process (often similar to CRISP-DM).
|
||||
|
||||
## Steps in the Process
|
||||
1. **Define the Goal**: What do you want to achieve? (e.g., Increase sales, detect fraud).
|
||||
2. **Gather Data**: Collect data from databases, logs, etc.
|
||||
3. **Cleanse Data**: Fix errors, remove duplicates, and handle missing values.
|
||||
4. **Interrogate Data**: Explore the data (charts, graphs) to find initial patterns.
|
||||
5. **Build a Model**: Use algorithms (like decision trees or regression) to find the solution.
|
||||
6. **Validate Results**: Check if the model is accurate.
|
||||
7. **Implement**: Use the insights in the real world.
|
||||
|
||||
## Data Mining Functionalities
|
||||
Tasks are generally divided into two types:
|
||||
|
||||
### 1. Descriptive Mining
|
||||
- Describes what is in the data.
|
||||
- Finds patterns and relationships.
|
||||
- *Examples*: Clustering, Association Rules.
|
||||
|
||||
### 2. Predictive Mining
|
||||
- Predicts future or unknown values.
|
||||
- *Examples*: Classification, Regression, Prediction.
|
||||
Reference in New Issue
Block a user