### Examples with Ready-Made Responses in English:

—

### **Example 1**

**Request:**
Describe the data transformation needed for **raw sales transaction data** to be used in **sales performance analysis**.

**Response:**
To use the **raw sales transaction data** in **sales performance analysis**, the following data transformations are needed:
1. **Data Cleaning**: Remove any duplicate records, correct erroneous or incomplete data entries, and ensure consistent formatting across fields (e.g., date formats, product IDs).
2. **Data Aggregation**: Aggregate the data by time period (e.g., daily, weekly, monthly) and by product or region to analyze trends and identify patterns.
3. **Data Normalization**: Standardize currency values, ensuring all figures are in the same unit of measurement for consistency across the dataset.
4. **Calculation of Key Metrics**: Create derived fields, such as total sales revenue, average deal size, and conversion rate, to provide meaningful insights in the analysis.
5. **Data Enrichment**: If necessary, integrate external data sources (e.g., marketing campaigns or regional economic data) to add context and improve the accuracy of performance analysis.

These transformations will allow for a clean, structured dataset ready for analysis, providing valuable insights into sales trends and performance.

—

### **Example 2**

**Request:**
Describe the data transformation needed for **customer satisfaction survey responses** to be used in **customer experience report**.

**Response:**
To prepare **customer satisfaction survey responses** for use in a **customer experience report**, the following transformations are required:
1. **Data Standardization**: Ensure consistency in response scales (e.g., converting all responses to a 1-5 or 1-10 scale) to facilitate comparisons across questions and surveys.
2. **Data Cleaning**: Address any missing or incomplete responses by either imputing missing values or removing records with insufficient data.
3. **Categorization**: Group open-ended responses into common themes or categories (e.g., service quality, product features, delivery time) for more actionable insights.
4. **Sentiment Analysis**: For open-ended feedback, perform sentiment analysis to quantify customer emotions (positive, neutral, or negative) and tie it back to the overall customer experience.
5. **Aggregation**: Aggregate the data by relevant segments such as customer demographics, purchase history, or service channels to identify trends and actionable insights.

These transformations will allow for a clear, actionable customer experience report that highlights key areas for improvement.

—

### **Example 3**

**Request:**
Describe the data transformation needed for **website traffic data** to be used in **digital marketing campaign performance analysis**.

**Response:**
To use **website traffic data** in **digital marketing campaign performance analysis**, the following steps are necessary:
1. **Data Cleaning**: Eliminate bot traffic and any irrelevant data points (e.g., internal company traffic) to ensure accurate traffic metrics.
2. **Data Aggregation**: Group traffic data by campaign source (e.g., social media, paid ads, organic search) and by key metrics (e.g., page views, bounce rate, conversion rate).
3. **Data Segmentation**: Break down traffic by user segments such as device type, geographic location, and demographics to understand campaign performance across different audience groups.
4. **Time Series Analysis**: Transform the data to analyze trends over time, allowing for comparisons of campaign performance week-over-week or month-over-month.
5. **Calculation of Key Metrics**: Calculate campaign-specific metrics, such as cost per acquisition (CPA), return on investment (ROI), and engagement rate, to measure the success of each campaign.

These transformations will ensure that the website traffic data is properly structured for analyzing the effectiveness of digital marketing efforts.

—

### **Example 4**

**Request:**
Describe the data transformation needed for **employee attendance records** to be used in **workforce productivity analysis**.

**Response:**
To prepare **employee attendance records** for **workforce productivity analysis**, the following data transformations are required:
1. **Data Cleaning**: Identify and correct any missing, duplicated, or inconsistent attendance entries, such as incorrect clock-in times or absent dates.
2. **Time Aggregation**: Aggregate the attendance data by employee and time period (e.g., weekly or monthly) to measure attendance patterns and trends.
3. **Calculation of Key Metrics**: Derive productivity-related metrics, such as absenteeism rate, late arrivals, and overtime hours, which impact overall workforce productivity.
4. **Data Enrichment**: If available, combine the attendance data with other performance indicators, such as task completion rates or employee satisfaction scores, to provide a more holistic view of workforce productivity.
5. **Segmentation**: Segment the data by departments, job roles, or tenure to assess how different employee groups contribute to overall productivity.

These transformations will help create a structured dataset for analyzing workforce productivity and identifying areas for improvement.

—

These descriptions provide clear and concise data transformation strategies, ensuring that raw data is properly prepared for meaningful analysis and decision-making.