Topic 1: Analytics Workflow

• Defining terms related to analytics and data science
• Describing the analytics workflow
• Explaining common usage scenarios
• Navigating Splunk Machine Learning Toolkit

Topic 2: Exploratory Data Analysis

• Describing the purpose of data exploration
• Identifying SPL commands for data exploration
• Splitting data for testing and training using the sample command

Topic 3: Predict Numeric Fields with Regression

• Differentiating predictions from estimates
• Identifying prediction algorithms and assumptions
• Describing the fit and apply commands
• Modeling numeric predictions in the MLTK and Splunk Enterprise
• Using the score command to evaluate models

Topic 4: Clean and Preprocess the Data

• Defining preprocessing and describing its purpose
• Describing algorithms for data preprocessing
• Using FieldSelector to choose relevant fields
• Using PCA and ICA to reduce dimensionality
• Normalizing data with StandardScaler and RobustScaler
• Preprocessing text using Imputer, NPR, TF-IDF, HashingVectorizer, and the cluster command

Topic 5: Cluster Data

• Defining clustering
• Identifying clustering methods, algorithms, and use cases
• Using Smart Clustering Assistant to cluster data
• Evaluating clusters using silhouette score
• Validating cluster coherence
• Describing clustering best practices

Topic 6: Anomaly Detection

• Defining anomaly detection and outliers
• Identifying anomaly detection use cases
• Using Splunk Machine Learning Toolkit Smart Outlier Assistant
• Detecting anomalies using the Density Function algorithm
• Optimizing anomaly detection with the Local Outlier Factor
• Viewing results with the Distribution Plot visualization

Topic 7: Estimation and Prediction

• Differentiating predictions from forecasts
• Using the Smart Forecasting Assistant
• Using the StateSpaceForecast algorithm
• Forecasting multivariate data
• Accounting for periodicity in each time series

Topic 8: Classification

• Defining key classification terms
• Using classification algorithms, including AutoPrediction, LogisticRegression, SVM (Support Vector Machines), and RandomForestClassifier
• Evaluating classifier tradeoffs
• Evaluating results of multiple algorithms

To excel in this course, students should have a solid understanding of the following prerequisites:

From the Fundamentals Series:

• Splunk Fundamentals 1
• Splunk Fundamentals 2
• Splunk Fundamentals 3

Alternatively, students should have a comprehensive grasp of the following single-subject courses:

• What is Splunk?
• Intro to Splunk
• Using Fields
• Scheduling Reports and Alerts
• Visualizations
• Working with Time
• Statistical Processing
• Comparing Values
• Result Modification
• Leveraging Lookups and Sub-searches
• Correlation Analysis
• Search Under the Hood
• Introduction to Knowledge Objects
• Creating Field Extractions
• Search Optimization