microsoft partner logo color
8245  Reviews star_rate star_rate star_rate star_rate star_half

Foundations of Machine Learning: Bridging Business Intelligence and Data Science

In this Machine Learning course, learners are introduced to essential machine learning (ML) topics, with a focus on intuitive and simplified explanations of key concepts, techniques, and...

Read More
Course Code WA3688
Duration 2 days
Available Formats Classroom

In this Machine Learning course, learners are introduced to essential machine learning (ML) topics, with a focus on intuitive and simplified explanations of key concepts, techniques, and applications. Using Microsoft Excel, the course demystifies ML by breaking down complex algorithms into their core components. Learners gain insights into regression, time-series forecasting, and model diagnostics without requiring a background in mathematics or programming. The course highlights the how and why of ML techniques and their practical relevance to both business intelligence and data science use cases. This is not a coding course but a foundational program designed to build a deep conceptual understanding of machine learning techniques and their applications. It is particularly suited for participants with a basic background in business intelligence who are looking to transition into a data science role.

Skills Gained

  • Break down complex machine learning techniques into simple, intuitive concepts
  • Develop a clear understanding of linear and non-linear regression, model diagnostics, and time-series forecasting
  • Explore the relevance of machine learning in business intelligence contexts
  • Gain familiarity with Microsoft Excel as a tool to visualize and understand machine learning algorithms
  • Understand the “when” and “why” of deploying machine learning tools and techniques
  • Build a foundational understanding of core machine learning concepts without requiring a math or coding background

Prerequisites

  • No prior coding or advanced math background is required
  • Familiarity with Excel
  • Familiarity with general business intelligence or data analysis concepts is helpful
  • Interest in understanding machine learning techniques and their practical applications

Course Details

Software Requirements

  • Microsoft Excel

Introduction to Machine Learning

  • Differences between Business Intelligence and Data Science
  • Machine Learning role in Business Intelligence and Data science
  • Overview of the machine learning landscape
  • Differences between supervised and unsupervised learning
  • Key concepts: feature engineering, overfitting, and regularization
  • Introduction to machine learning workflows and applications

Data Quality Assessment and Profiling

  • Assessing preliminary data quality: variable types, empty values, and data structure
  • Exploring univariate data: distributions, histograms, and kernel densities
  • Profiling metrics for variable analysis
  • Multivariate profiling: correlations and variance
  • Visualizations like box plots, violin plots, and kernel density plots

Supervised Learning: Classification

  • Overview of the classification process
  • Feature engineering and data preparation
  • Splitting data into training and testing sets
  • Addressing overfitting and underfitting
  • Common classification models: K-Nearest Neighbors (KNN), Naive Bayes, Decision Trees, Random Forests, and Logistic Regression
  • Handling imbalanced classes
  • Understanding and addressing model drift
  • Evaluating performance: confusion matrices and other metrics
  • Practical application: sentiment analysis

Supervised Learning: Regression

  • Differentiating regression from classification
  • Key concepts: linear relationships, least-squared error, and multivariate regression
  • Non-linear regression models
  • Regularization methods to address overfitting
  • Diagnosing regression models
  • Interpreting R-squared, mean error, F-significance, and P-values
  • Identifying and addressing model shortcomings

Time-Series Forecasting

  • Fundamentals of time-series data
  • Analyzing seasonality, trends, and patterns
  • Techniques for forecasting
  • Linear and non-linear forecasting models
  • Intervention analysis
  • Applying time-series models for business intelligence

Unsupervised Learning: Segmentation and Clustering

  • Foundations of unsupervised learning
  • Key workflows in segmentation and clustering
  • Clustering methods
  • K-Means Clustering
  • Hierarchical Clustering

Unsupervised Learning: Association Mining

  • Introduction to association rule mining
  • A Priori algorithm: concepts and implementation
  • Markov models for association mining

Outlier Detection

  • Cross-sectional outlier detection techniques
  • Nearest Neighbor Distance method
  • Identifying outliers in time-series data

Dimensionality Reduction

  • Foundations of dimensionality reduction
  • Techniques for reducing dimensions in datasets
  • Principal Component Analysis (PCA)
  • Singular Value Decomposition (SVD)