Big Data Business Intelligence for Govt. Agencies Training Course

Each session lasts 2 hours

Day 1: Session 1: Business Overview of Big Data Business Intelligence in Government

• Case studies from NIH and DoE
• Big Data adoption rates in government agencies and the alignment of future operations with Big Data Predictive Analytics
• Widescale application areas in DoD, NSA, IRS, USDA, etc.
• Interfacing Big Data with legacy data systems
• Basic understanding of enabling technologies in predictive analytics
• Data integration and dashboard visualization
• Fraud management
• Generation of business rules and fraud detection
• Threat detection and profiling
• Cost-benefit analysis for Big Data implementation

Day 1: Session 2: Introduction to Big Data-1

• Core characteristics of Big Data: volume, variety, velocity, and veracity. MPP architecture for volume management.
• Data warehouses – static schemas and slowly evolving datasets
• MPP databases such as Greenplum, Exadata, Teradata, Netezza, Vertica, etc.
• Hadoop-based solutions – no structural constraints on datasets.
• Typical pattern: HDFS, MapReduce (crunch), retrieval from HDFS
• Batch processing – suited for analytical/non-interactive tasks
• Velocity: CEP streaming data
• Typical choices – CEP products (e.g., Infostreams, Apama, MarkLogic, etc.)
• Less production-ready options – Storm/S4
• NoSQL databases – (columnar and key-value): Ideal as an analytical adjunct to data warehouses/databases

Day 1: Session 3: Introduction to Big Data-2

NoSQL Solutions

• KV Store - Keyspace, Flare, SchemaFree, RAMCloud, Oracle NoSQL Database (OnDB)
• KV Store - Dynamo, Voldemort, Dynomite, SubRecord, Mo8onDb, DovetailDB
• KV Store (Hierarchical) - GT.m, Cache
• KV Store (Ordered) - TokyoTyrant, Lightcloud, NMDB, Luxio, MemcacheDB, Actord
• KV Cache - Memcached, Repcached, Coherence, Infinispan, EXtremeScale, JBossCache, Velocity, Terracoqua
• Tuple Store - Gigaspaces, Coord, Apache River
• Object Database - ZopeDB, DB40, Shoal
• Document Store - CouchDB, Cloudant, Couchbase, MongoDB, Jackrabbit, XML-Databases, ThruDB, CloudKit, Prsevere, Riak-Basho, Scalaris
• Wide Columnar Store - BigTable, HBase, Apache Cassandra, Hypertable, KAI, OpenNeptune, Qbase, KDI

Varieties of Data: Introduction to Data Cleaning Challenges in Big Data

• RDBMS – static structure/schema; does not promote an agile, exploratory environment.
• NoSQL – semi-structured; sufficient structure to store data without defining an exact schema beforehand
• Data cleaning issues

Day 1: Session 4: Big Data Introduction-3: Hadoop

• When to choose Hadoop?
• STRUCTURED - Enterprise data warehouses/databases can store massive data (at a cost) but impose structure (not ideal for active exploration)
• SEMI-STRUCTURED data – difficult to handle with traditional solutions (DW/DB)
• Warehousing data requires significant effort and remains static even after implementation
• For data variety and volume, processed on commodity hardware – HADOOP
• Commodity hardware is required to create a Hadoop cluster

Introduction to MapReduce /HDFS

• MapReduce – distributes computing across multiple servers
• HDFS – makes data available locally for the computing process (with redundancy)
• Data – can be unstructured/schema-less (unlike RDBMS)
• Developer responsibility to interpret and make sense of data
• Programming MapReduce involves working with Java (pros/cons) and manually loading data into HDFS

Day 2: Session 1: Big Data Ecosystem – Building Big Data ETL: The Universe of Big Data Tools – Which to Use and When?

• Hadoop vs. other NoSQL solutions
• Interactive, random access to data
• Hbase (column-oriented database) on top of Hadoop
• Random access to data but with restrictions (max 1 PB)
• Not ideal for ad-hoc analytics; suitable for logging, counting, and time-series data
• Sqoop – imports from databases to Hive or HDFS (JDBC/ODBC access)
• Flume – streams data (e.g., log data) into HDFS

Day 2: Session 2: Big Data Management System

• Moving parts, compute node start/fail: ZooKeeper – for configuration/coordination/naming services
• Complex pipelines/workflows: Oozie – manages workflows, dependencies, and chains
• Deployment, configuration, cluster management, upgrades, etc. (sysadmin): Ambari
• In Cloud: Whirr

Day 2: Session 3: Predictive Analytics in Business Intelligence -1: Fundamental Techniques & Machine Learning based BI

• Introduction to machine learning
• Learning classification techniques
• Bayesian Prediction – preparing training files
• Support Vector Machine
• KNN p-Tree Algebra & vertical mining
• Neural Networks
• Big Data large variable problem – Random Forest (RF)
• Big Data Automation problem – Multi-model ensemble RF
• Automation through Soft10-M
• Text analytic tool – Treeminer
• Agile learning
• Agent-based learning
• Distributed learning
• Introduction to open-source tools for predictive analytics: R, Rapidminer, Mahut

Day 2: Session 4: Predictive Analytics Ecosystem-2: Common Predictive Analytic Problems in Government

• Insight analytics
• Visualization analytics
• Structured predictive analytics
• Unstructured predictive analytics
• Threat/fraudster/vendor profiling
• Recommendation engines
• Pattern detection
• Rule/Scenario discovery – failure, fraud, optimization
• Root cause discovery
• Sentiment analysis
• CRM analytics
• Network analytics
• Text analytics
• Technology-assisted review
• Fraud analytics
• Real-time analytics

Day 3: Session 1: Real-Time and Scalable Analytics over Hadoop

• Why common analytic algorithms fail in Hadoop/HDFS
• Apache Hama – for Bulk Synchronous distributed computing
• Apache SPARK – for cluster computing for real-time analytics
• CMU Graphics Lab2 – Graph-based asynchronous approach to distributed computing
• KNN p-Algebra based approach from Treeminer for reduced hardware costs of operation

Day 3: Session 2: Tools for eDiscovery and Forensics

• eDiscovery over Big Data vs. Legacy data – comparison of cost and performance
• Predictive coding and technology-assisted review (TAR)
• Live demo of a TAR product (vMiner) to understand how TAR works for faster discovery
• Faster indexing through HDFS – velocity of data
• NLP or Natural Language Processing – various techniques and open-source products
• eDiscovery in foreign languages – technology for foreign language processing

Day 3: Session 3: Big Data BI for Cyber Security – Understanding the 360-degree view from speedy data collection to threat identification

• Understanding the basics of security analytics: attack surface, security misconfiguration, host defenses
• Network infrastructure/Large data pipes/Response ETL for real-time analytics
• Prescriptive vs. predictive – fixed rule-based vs. auto-discovery of threat rules from metadata

Day 3: Session 4: Big Data in USDA: Applications in Agriculture

• Introduction to IoT (Internet of Things) for agriculture: sensor-based Big Data and control
• Introduction to satellite imaging and its application in agriculture
• Integrating sensor and image data for soil fertility, cultivation recommendations, and forecasting
• Agriculture insurance and Big Data
• Crop loss forecasting

Day 4: Session 1: Fraud Prevention BI from Big Data in Government: Fraud Analytics

• Basic classification of Fraud analytics: rule-based vs. predictive analytics
• Supervised vs. unsupervised machine learning for Fraud pattern detection
• Vendor fraud/overcharging for projects
• Medicare and Medicaid fraud: fraud detection techniques for claim processing
• Travel reimbursement frauds
• IRS refund frauds
• Case studies and live demos will be provided where data is available.

Day 4: Session 2: Social Media Analytics: Intelligence Gathering and Analysis

• Big Data ETL API for extracting social media data
• Text, image, metadata, and video
• Sentiment analysis from social media feeds
• Contextual and non-contextual filtering of social media feeds
• Social Media Dashboard to integrate diverse social media sources
• Automated profiling of social media profiles
• Live demo of each analytic will be given through the Treeminer Tool.

Day 4: Session 3: Big Data Analytics in Image Processing and Video Feeds

• Image storage techniques in Big Data: storage solutions for data exceeding petabytes
• LTFS and LTO
• GPFS-LTFS (Layered storage solution for Big image data)
• Fundamentals of image analytics
• Object recognition
• Image segmentation
• Motion tracking
• 3-D image reconstruction

Day 4: Session 4: Big Data Applications in NIH

• Emerging areas of Bio-informatics
• Meta-genomics and Big Data mining issues
• Big Data Predictive analytics for Pharmacogenomics, Metabolomics, and Proteomics
• Big Data in downstream Genomics processes
• Application of Big Data predictive analytics in Public health

Big Data Dashboard for Quick Accessibility of Diverse Data and Display

• Integration of existing application platforms with Big Data Dashboards
• Big Data management
• Case Study of Big Data Dashboard: Tableau and Pentaho
• Use of Big Data apps to push location-based services in Government
• Tracking systems and management

Day 5: Session 1: Justifying Big Data BI Implementation within an Organization

• Defining ROI for Big Data implementation
• Case studies for saving Analyst Time in data collection and preparation – increase in productivity gain
• Case studies of revenue gain from saving licensed database costs
• Revenue gain from location-based services
• Savings from fraud prevention
• An integrated spreadsheet approach to calculate approximate expense vs. revenue gain/savings from Big Data implementation.

Day 5: Session 2: Step-by-Step Procedure to Replace Legacy Data Systems with Big Data Systems

• Understanding a practical Big Data Migration Roadmap
• Key information needed before architecting a Big Data implementation
• Methods for calculating the volume, velocity, variety, and veracity of data
• Estimating data growth
• Case studies

Day 5: Session 4: Review of Big Data Vendors and their Products. Q/A Session:

• Accenture
• APTEAN (Formerly CDC Software)
• Cisco Systems
• Cloudera
• Dell
• EMC
• GoodData Corporation
• Guavus
• Hitachi Data Systems
• Hortonworks
• HP
• IBM
• Informatica
• Intel
• Jaspersoft
• Microsoft
• MongoDB (Formerly 10Gen)
• MU Sigma
• Netapp
• Opera Solutions
• Oracle
• Pentaho
• Platfora
• Qliktech
• Quantum
• Rackspace
• Revolution Analytics
• Salesforce
• SAP
• SAS Institute
• Sisense
• Software AG/Terracotta
• Soft10 Automation
• Splunk
• Sqrrl
• Supermicro
• Tableau Software
• Teradata
• Think Big Analytics
• Tidemark Systems
• Treeminer
• VMware (Part of EMC)