High-quality data preparation is one of the most important steps in building successful machine learning solutions. The Python Machine Learning Client (hana-ml) provides HANA DataFrames that enable developers and data scientists to perform data exploration, cleansing, transformation, feature engineering, and visualization directly within SAP HANA Cloud, minimizing data movement and improving performance.

This module introduces HANA DataFrames, data loading, exploratory data analysis (EDA), data cleansing, feature engineering, and data visualization techniques required before training machine learning models.

By the end of this module, learners will be able to prepare enterprise datasets for machine learning using SAP HANA Cloud and the Python Machine Learning Client.

According to the SAP Learning Journey, this module covers HANA DataFrames, exploratory data analysis, data preparation, feature engineering, and visualization techniques.

What You Will Learn

• Load enterprise datasets into HANA DataFrames.
• Perform exploratory data analysis (EDA).
• Clean and transform datasets.
• Handle missing values.
• Engineer machine learning features.
• Visualize business data.
• Prepare datasets for model training.
• Optimize data quality for AI workflows.

Units in This Module

• Unit 2.1: Loading Enterprise Data into HANA DataFrames
• Unit 2.2: Performing Exploratory Data Analysis (EDA)
• Unit 2.3: Cleaning and Transforming Data
• Unit 2.4: Feature Engineering for Machine Learning
• Unit 2.5: Visualizing Business Data

HANA DataFrames provide a Python interface for working directly with SAP HANA Cloud tables. Participants will learn how to import enterprise datasets, access database tables, inspect schemas, and prepare data for analysis without extracting information from the database.

Key Topics

• HANA DataFrames
• Data Loading
• SAP HANA Tables
• Database Access
• Enterprise Datasets
• SQL Integration
• Data Inspection
• Python Integration

Exploratory Data Analysis helps data scientists understand dataset characteristics before building machine learning models. Learners will examine data distributions, identify trends, detect anomalies, and summarize business data using HANA DataFrames.

Key Topics

• Exploratory Data Analysis (EDA)
• Data Profiling
• Statistical Summary
• Data Distribution
• Pattern Discovery
• Outlier Detection
• Business Analytics
• SAP HANA

Data cleansing improves machine learning accuracy by correcting inconsistencies, handling missing values, removing duplicates, and transforming raw data into a structured format suitable for predictive modeling.

Key Topics

• Data Cleansing
• Data Transformation
• Missing Values
• Duplicate Removal
• Data Standardization
• Data Quality
• Enterprise Data
• Machine Learning Preparation

Feature engineering transforms raw business data into meaningful variables that improve model performance. Participants will learn how to create, modify, and optimize features using HANA DataFrames and SAP HANA processing capabilities.

Key Topics

• Feature Engineering
• Feature Selection
• Derived Features
• Data Transformation
• Machine Learning Features
• Predictive Analytics
• Data Preparation
• SAP HANA

Data visualization enables analysts to identify relationships, trends, and business insights before model development. Learners will use Python visualization libraries together with HANA DataFrames to create informative charts and graphical summaries.

Key Topics

• Data Visualization
• Charts
• Graphs
• Business Insights
• Data Analytics
• Trend Analysis
• Python Visualization
• SAP HANA

Regression models are widely used in machine learning to predict continuous numerical values such as housing prices, sales revenue, demand forecasts, and financial metrics. The SAP HANA Predictive Analysis Library (PAL) provides high-performance, in-database machine learning algorithms that enable developers to train and evaluate regression models without moving data outside SAP HANA Cloud.

This module introduces regression analysis, the California Housing dataset, model training, prediction, evaluation, and regression workflows using the Python Machine Learning Client (hana-ml) and SAP HANA PAL.

By the end of this module, learners will be able to prepare datasets, train regression models, generate predictions, evaluate model accuracy, and build enterprise-grade predictive analytics solutions.

According to the SAP Learning Journey, this module covers regression modeling using the California Housing dataset, model training, prediction, and evaluation with the Predictive Analysis Library (PAL).

What You Will Learn

• Understand regression analysis.
• Prepare data for regression models.
• Train regression models using PAL.
• Generate business predictions.
• Evaluate regression model performance.
• Interpret regression results.
• Optimize predictive models.
• Build enterprise regression workflows.

Units in This Module

• Unit 3.1: Understanding Regression Analysis
• Unit 3.2: Preparing the California Housing Dataset
• Unit 3.3: Training Regression Models with PAL
• Unit 3.4: Making Predictions
• Unit 3.5: Evaluating Regression Models

Regression analysis is a supervised machine learning technique used to predict continuous numerical outcomes based on historical data. Participants will understand regression concepts, business use cases, and predictive modeling principles.

Key Topics

• Regression Analysis
• Supervised Learning
• Predictive Modeling
• Continuous Variables
• Machine Learning
• Business Forecasting
• SAP HANA PAL
• Enterprise Analytics

The California Housing dataset is used to demonstrate regression modeling techniques. Learners will prepare, explore, and transform housing data before training predictive models using SAP HANA Cloud.

Key Topics

• California Housing Dataset
• Data Preparation
• Data Cleansing
• Feature Engineering
• HANA DataFrames
• Exploratory Data Analysis
• Data Transformation
• Machine Learning

Participants will train regression models using the SAP HANA Predictive Analysis Library (PAL), leveraging in-database processing to improve scalability and performance while minimizing data movement.

Key Topics

• Predictive Analysis Library (PAL)
• Regression Models
• Model Training
• In-Database Machine Learning
• SAP HANA Cloud
• hana-ml
• Machine Learning Algorithms
• AI Development

After training regression models, learners will generate predictions using unseen data and understand how predictive analytics supports business decision-making across enterprise scenarios.

Key Topics

• Predictions
• Regression Inference
• Business Forecasting
• Predictive Analytics
• Model Deployment
• Enterprise AI
• SAP HANA
• Machine Learning

Model evaluation measures the effectiveness and accuracy of regression models using standard performance metrics. Participants will analyze prediction quality and identify opportunities for model improvement.

Key Topics

• Model Evaluation
• Mean Squared Error (MSE)
• Root Mean Squared Error (RMSE)
• R² Score
• Prediction Accuracy
• Performance Metrics
• Model Validation
• Enterprise Analytics

Classification models are used to predict categorical outcomes such as customer churn, fraud detection, loan approval, product recommendations, and customer segmentation. The SAP HANA Predictive Analysis Library (PAL) enables developers to build high-performance classification models directly within SAP HANA Cloud using the Python Machine Learning Client (hana-ml).

This module introduces supervised classification techniques, employee churn prediction, HANA DataFrames, PAL classification algorithms, model training, prediction, evaluation, and enterprise AI workflows.

By the end of this module, learners will be able to prepare classification datasets, build predictive classification models, evaluate model performance, and apply machine learning techniques to solve real-world business problems.

According to the SAP Learning Journey, this module covers classification modeling, employee churn prediction, HANA DataFrames, Predictive Analysis Library (PAL), model training, and evaluation.

What You Will Learn

• Understand supervised classification.
• Prepare data for classification models.
• Configure the Python Machine Learning Client.
• Train classification models using PAL.
• Predict employee churn.
• Evaluate classification performance.
• Interpret classification results.
• Build enterprise AI classification workflows.

Units in This Module

• Unit 4.1: Understanding Classification with SAP HANA
• Unit 4.2: Setting Up the Environment and Analyzing Data with HANA DataFrames
• Unit 4.3: Training a PAL Classification Model for Employee Churn Prediction
• Unit 4.4: Evaluating and Testing Classification Models

Classification is a supervised machine learning technique that predicts categorical outcomes using historical data. Participants will understand classification concepts, business applications, and how SAP HANA PAL supports enterprise classification models.

Key Topics

• Classification
• Supervised Learning
• Machine Learning
• Categorical Prediction
• Predictive Analytics
• SAP HANA PAL
• Business Intelligence
• Enterprise AI

Before training classification models, learners will configure the Python Machine Learning Client, connect to SAP HANA Cloud, access enterprise datasets using HANA DataFrames, and perform exploratory data analysis to understand employee churn patterns.

Key Topics

• Python Machine Learning Client (hana-ml)
• SAP HANA Cloud
• HANA DataFrames
• Data Analysis
• Employee Churn Dataset
• Data Exploration
• Feature Analysis
• Enterprise Data

Participants will build and train a classification model using the SAP HANA Predictive Analysis Library (PAL) to predict employee churn based on historical employee data. The unit demonstrates how enterprise organizations can identify employees at risk of leaving and support proactive retention strategies.

Key Topics

• Predictive Analysis Library (PAL)
• Classification Model
• Employee Churn Prediction
• Model Training
• Supervised Learning
• SAP HANA Cloud
• AI Development
• Predictive Analytics

Model evaluation determines how effectively a classification model predicts business outcomes. Learners will evaluate trained models using standard classification metrics and validate prediction accuracy before deployment.

Key Topics

• Model Evaluation
• Accuracy
• Precision
• Recall
• F1 Score
• Confusion Matrix
• Model Validation
• Performance Analysis

Time series forecasting enables organizations to predict future values based on historical trends, seasonality, and business patterns. SAP HANA's Predictive Analysis Library (PAL) provides advanced forecasting algorithms that allow developers to build scalable forecasting solutions directly within SAP HANA Cloud using the Python Machine Learning Client (hana-ml).

This module introduces time series forecasting concepts, HANA DataFrames, forecasting model development, PAL time series algorithms, prediction generation, and model evaluation.

By the end of this module, learners will be able to build forecasting models for enterprise business scenarios such as overnight stays, sales forecasting, inventory planning, and demand prediction.

According to the SAP Learning Journey, this module covers time series forecasting, HANA DataFrames, Predictive Analysis Library (PAL), forecasting models, and model evaluation.

What You Will Learn

• Understand time series forecasting.
• Prepare time series datasets.
• Configure forecasting models.
• Train PAL forecasting models.
• Generate future predictions.
• Evaluate forecasting accuracy.
• Interpret forecasting results.
• Build enterprise forecasting workflows.

Units in This Module

• Unit 5.1: Understanding Machine Learning for Time Series Forecasting
• Unit 5.2: Setting Up the Environment and Preparing Data Using HANA DataFrames
• Unit 5.3: Training an SAP HANA PAL Univariate Time Series Model
• Unit 5.4: Forecasting with Multiple Time Series

Time series forecasting predicts future events based on historical observations. Participants will understand forecasting concepts, trend analysis, seasonality, cyclic behavior, and enterprise forecasting use cases.

Key Topics

• Time Series Forecasting
• Trend Analysis
• Seasonality
• Forecasting Models
• Predictive Analytics
• Business Forecasting
• Machine Learning
• SAP HANA PAL

Learners will configure the Python Machine Learning Client, prepare time series datasets using HANA DataFrames, perform data transformations, and prepare historical business data for forecasting model development.

Key Topics

• HANA DataFrames
• Time Series Data
• Data Preparation
• Data Transformation
• Python Machine Learning Client
• SAP HANA Cloud
• Feature Engineering
• Enterprise Data

Participants will build a univariate forecasting model using SAP HANA Predictive Analysis Library (PAL), training the model on historical overnight stay data to generate accurate future forecasts.

Key Topics

• Predictive Analysis Library (PAL)
• Univariate Forecasting
• Model Training
• SAP HANA Cloud
• Time Series Algorithms
• AI Development
• Forecast Modeling
• Enterprise Analytics

Organizations often analyze multiple related time series simultaneously to improve forecasting accuracy. Learners will explore multi-series forecasting techniques and understand how SAP HANA PAL supports enterprise forecasting scenarios.

Key Topics

• Multiple Time Series
• Forecast Generation
• Business Forecasting
• Predictive Analytics
• Time Series Analysis
• SAP HANA PAL
• Enterprise AI
• Forecast Optimization

Developing enterprise AI solutions requires more than training individual machine learning models. Organizations need complete AI workflows that integrate data preparation, model development, evaluation, prediction, optimization, and deployment into repeatable business processes. The Python Machine Learning Client (hana-ml) and SAP HANA Cloud provide an integrated platform for building scalable, production-ready machine learning pipelines using the Predictive Analysis Library (PAL).

This module brings together the concepts learned throughout the course to create complete AI workflows, from data ingestion to predictive analytics, using SAP HANA Cloud and Python.

By the end of this module, learners will be able to design, implement, evaluate, and optimize end-to-end machine learning workflows for enterprise business scenarios.

According to the SAP Learning Journey, this module focuses on integrating data preparation, regression, classification, forecasting, evaluation, and enterprise AI workflows using the Python Machine Learning Client and SAP HANA Cloud.

What You Will Learn

• Design complete AI workflows.
• Integrate data preparation with machine learning.
• Combine regression, classification, and forecasting models.
• Evaluate and compare machine learning models.
• Optimize enterprise AI pipelines.
• Automate AI workflows using Python.
• Apply AI to real-world business scenarios.
• Build production-ready machine learning solutions.

Units in This Module

• Unit 6.1: Designing Enterprise AI Workflows
• Unit 6.2: Integrating Data Preparation and Machine Learning
• Unit 6.3: Evaluating and Comparing Machine Learning Models
• Unit 6.4: Building Production-Ready AI Solutions

Enterprise AI workflows combine data preparation, feature engineering, machine learning, evaluation, and prediction into structured business processes. Participants will understand the architecture of AI workflows using SAP HANA Cloud and the Python Machine Learning Client.

Key Topics

• Enterprise AI
• AI Workflow Design
• Machine Learning Pipeline
• SAP HANA Cloud
• Business Analytics
• Predictive Analytics
• Python Integration
• AI Architecture

High-quality machine learning depends on well-prepared data. Learners will integrate HANA DataFrames, feature engineering, data transformation, and PAL algorithms into a unified workflow for enterprise AI development.

Key Topics

• HANA DataFrames
• Data Preparation
• Feature Engineering
• Data Transformation
• Machine Learning Pipeline
• SAP HANA PAL
• Enterprise Data
• Workflow Automation

Organizations often build multiple machine learning models before selecting the best-performing solution. Participants will compare regression, classification, and forecasting models using evaluation metrics and business performance indicators.

Key Topics

• Model Comparison
• Model Evaluation
• Performance Metrics
• Regression
• Classification
• Forecasting
• Predictive Analytics
• Enterprise AI

Production-ready AI solutions require scalable workflows, reusable Python code, secure SAP HANA Cloud integration, and optimized machine learning models. Learners will understand best practices for developing enterprise-grade AI applications.

Key Topics

• Production Deployment
• AI Solutions
• Enterprise Applications
• SAP HANA Cloud
• Python Automation
• Workflow Optimization
• Business Intelligence
• Cloud AI

Throughout this course, learners will complete hands-on exercises using the Python Machine Learning Client (hana-ml) and SAP HANA Cloud to develop complete enterprise AI workflows.

Participants will perform the following practical activities:

• Install and configure the Python Machine Learning Client (hana-ml)
• Connect Python applications to SAP HANA Cloud
• Load enterprise datasets using HANA DataFrames
• Perform exploratory data analysis (EDA)
• Clean and transform business data
• Engineer machine learning features
• Build regression models using SAP HANA PAL
• Predict California housing prices
• Build classification models for employee churn prediction
• Evaluate classification performance using confusion matrices and accuracy metrics
• Build univariate time series forecasting models
• Generate business forecasts
• Compare machine learning model performance
• Optimize predictive models
• Design end-to-end AI workflows
• Automate machine learning processes using Python
• Develop enterprise AI solutions with SAP HANA Cloud

Developing an Enterprise AI Solution Using the Python Machine Learning Client for SAP HANA

In this capstone project, learners will build a complete enterprise machine learning solution using SAP HANA Cloud, the Python Machine Learning Client (hana-ml), HANA DataFrames, and the Predictive Analysis Library (PAL).

Participants will design an end-to-end AI workflow that includes data preparation, regression analysis, classification, forecasting, model evaluation, and workflow optimization while following SAP AI development best practices.

The implementation project follows the complete SAP Learning Journey for developing AI workflows with the Python Machine Learning Client for SAP HANA.

Phase 1 – Environment Setup

Configure:

• Python Development Environment
• Python Machine Learning Client (hana-ml)
• SAP HANA Cloud Connectivity
• HANA DataFrames
• Project Structure
• Development Tools
• Authentication
• Enterprise Workspace

Phase 2 – Data Preparation

Implement:

• Enterprise Dataset Loading
• Data Cleansing
• Feature Engineering
• Exploratory Data Analysis
• Data Transformation
• Dataset Validation
• Statistical Analysis
• Data Quality Checks

Phase 3 – Machine Learning Development

Build:

• Regression Models
• Classification Models
• Time Series Forecasting Models
• Predictive Analysis Library (PAL) Algorithms
• Business Predictions
• AI Pipelines
• Feature Selection
• Model Optimization

Phase 4 – Model Evaluation

Implement:

• Performance Metrics
• Model Comparison
• Accuracy Analysis
• Prediction Validation
• Error Analysis
• Forecast Evaluation
• Business Performance Measurement
• AI Optimization

Phase 5 – Enterprise AI Workflow

Develop:

• End-to-End AI Pipeline
• Automated Machine Learning Workflow
• Business Analytics Dashboard
• Predictive Reporting
• Enterprise AI Solution
• Workflow Optimization
• Scalable Machine Learning Architecture
• AI Best Practices

Expected Project Outcome

Upon successful completion of this implementation project, learners will be able to:

• Configure the Python Machine Learning Client (hana-ml).
• Connect securely to SAP HANA Cloud.
• Prepare enterprise datasets using HANA DataFrames.
• Build regression, classification, and forecasting models.
• Evaluate and compare machine learning models.
• Design complete AI workflows.
• Optimize enterprise machine learning pipelines.
• Develop scalable AI solutions using SAP HANA Cloud.