Visão Geral

Neste Curso Big Data Business Intelligence for Criminal Intelligence Analysis, os avanços nas tecnologias e a quantidade crescente de informações estão transformando a maneira como a aplicação da lei é conduzida. Os desafios que o Big Data coloca são quase tão assustadores quanto a promessa do Big Data . Armazenar dados com eficiência é um desses desafios; efetivamente analisá-lo é outro.

Objetivo

Ao final deste treinamento, os participantes serão capazes de:

1. Combine a tecnologia Big Data com os processos tradicionais de coleta de dados para reunir uma história durante uma investigação
2. Implementar soluções industriais de armazenamento e processamento de big data para análise de dados
3. Preparar uma proposta para a adoção das ferramentas e processos mais adequados para permitir uma abordagem baseada em dados à investigação criminal

Publico Alvo

• Especialistas em aplicação da lei com formação técnica

Pre-Requisitos

• Conhecimento de processos de aplicação da lei e sistemas de dados
• Noções básicas de SQL/Oracle ou banco de dados relacional
• Compreensão básica de estatísticas (no nível da planilha)

Informações Gerais

Carga horaria: 40h

• Se noturno este curso e ministrado de segunda-feira a sexta-feira das 19h às 23h, total de 10 encontros.
• Se aos sábados este curso e ministrado das 09h às 18h, total de 5 encontros.

Formato de entrega:

• 100% on-line ao vivo via Microsoft Teams, na presença de um instrutor/consultor ativo no mercado e docente em sala de aula. 
• Nota: não é curso gravado (o mesmo acontece em tempo real na presença de um instrutor).
• Apostila + exercícios práticos

Materiais

Conteúdo Programatico

Day 01

Overview of Big Data Business Intelligence for Criminal Intelligence Analysis

1. Case Studies from Law Enforcement - Predictive Policing
   
2. Big Data adoption rate in Law Enforcement Agencies and how they are aligning their future operation around Big Data Predictive Analytics
3. Emerging technology solutions such as gunshot sensors, surveillance video and social media
4. Using Big Data technology to mitigate information overload
5. Interfacing Big Data with Legacy data
6. Basic understanding of enabling technologies in predictive analytics
7. Data Integration & Dashboard visualization
8. Fraud management
9. Business Rules and Fraud detection
10. Threat detection and profiling
11. Cost benefit analysis for Big Data implementation

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

1. RDBMS – static structure/schema, does not promote agile, exploratory environment.
2. NoSQL – semi structured, enough structure to store data without exact schema before storing data
3. Data cleaning issues

Hadoop

1. When to select Hadoop?
2. STRUCTURED - Enterprise data warehouses/databases can store massive data (at a cost) but impose structure (not good for active exploration)
3. SEMI STRUCTURED data – difficult to carry out using traditional solutions (DW/DB)
4. Warehousing data = HUGE effort and static even after implementation
5. For variety & volume of data, crunched on commodity hardware – HADOOP
6. Commodity H/W needed to create a Hadoop Cluster

Introduction to Map Reduce /HDFS

1. MapReduce – distribute computing over multiple servers
2. HDFS – make data available locally for the computing process (with redundancy)
3. Data – can be unstructured/schema-less (unlike RDBMS)
4. Developer responsibility to make sense of data
5. Programming MapReduce = working with Java (pros/cons), manually loading data into HDFS

Day 02

Big Data Ecosystem -- Building Big Data ETL (Extract, Transform, Load) -- Which Big Data Tools to use and when?

1. Hadoop vs. Other NoSQL solutions
2. For interactive, random access to data
3. Hbase (column oriented database) on top of Hadoop
4. Random access to data but restrictions imposed (max 1 PB)
5. Not good for ad-hoc analytics, good for logging, counting, time-series
6. Sqoop - Import from databases to Hive or HDFS (JDBC/ODBC access)
7. Flume – Stream data (e.g. log data) into HDFS

Big Data Management System

1. Moving parts, compute nodes start/fail :ZooKeeper - For configuration/coordination/naming services
2. Complex pipeline/workflow: Oozie – manage workflow, dependencies, daisy chain
3. Deploy, configure, cluster management, upgrade etc (sys admin) :Ambari
4. In Cloud : Whirr

Predictive Analytics -- Fundamental Techniques and Machine Learning based Business Intelligence

1. Introduction to Machine Learning
2. Learning classification techniques
3. Bayesian Prediction -- preparing a training file
4. Support Vector Machine
5. KNN p-Tree Algebra & vertical mining
6. Neural Networks
7. Big Data large variable problem -- Random forest (RF)
8. Big Data Automation problem – Multi-model ensemble RF
9. Automation through Soft10-M
10. Text analytic tool-Treeminer
11. Agile learning
12. Agent based learning
13. Distributed learning
14. Introduction to Open source Tools for predictive analytics : R, Python, Rapidminer, Mahut

Predictive Analytics Ecosystem and its application in Criminal Intelligence Analysis

1. Technology and the investigative process
2. Insight analytic
3. Visualization analytics
4. Structured predictive analytics
5. Unstructured predictive analytics
6. Threat/fraudstar/vendor profiling
7. Recommendation Engine
8. Pattern detection
9. Rule/Scenario discovery – failure, fraud, optimization
10. Root cause discovery
11. Sentiment analysis
12. CRM analytics
13. Network analytics
14. Text analytics for obtaining insights from transcripts, witness statements, internet chatter, etc.
15. Technology assisted review
16. Fraud analytics
17. Real Time Analytic

Day 03

Real Time and Scalable Analytics Over Hadoop

1. Why common analytic algorithms fail in Hadoop/HDFS
2. Apache Hama- for Bulk Synchronous distributed computing
3. Apache SPARK- for cluster computing and real time analytic
4. CMU Graphics Lab2- Graph based asynchronous approach to distributed computing
5. KNN p -- Algebra based approach from Treeminer for reduced hardware cost of operation

Tools for eDiscovery and Forensics

1. eDiscovery over Big Data vs. Legacy data – a comparison of cost and performance
2. Predictive coding and Technology Assisted Review (TAR)
3. Live demo of vMiner for understanding how TAR enables faster discovery
4. Faster indexing through HDFS – Velocity of data
5. NLP (Natural Language processing) – open source products and techniques
6. eDiscovery in foreign languages -- technology for foreign language processing

Big Data BI for Cyber Security – Getting a 360-degree view, speedy data collection and threat identification

1. Understanding the basics of security analytics -- attack surface, security misconfiguration, host defenses
2. Network infrastructure / Large datapipe / Response ETL for real time analytic
3. Prescriptive vs predictive – Fixed rule based vs auto-discovery of threat rules from Meta data

Gathering disparate data for Criminal Intelligence Analysis

1. Using IoT (Internet of Things) as sensors for capturing data
2. Using Satellite Imagery for Domestic Surveillance
3. Using surveillance and image data for criminal identification
4. Other data gathering technologies -- drones, body cameras, GPS tagging systems and thermal imaging technology
5. Combining automated data retrieval with data obtained from informants, interrogation, and research
6. Forecasting criminal activity

Day 04

Fraud prevention BI from Big Data in Fraud Analytics

1. Basic classification of Fraud Analytics -- rules-based vs predictive analytics
2. Supervised vs unsupervised Machine learning for Fraud pattern detection
3. Business to business fraud, medical claims fraud, insurance fraud, tax evasion and money laundering

Social Media Analytics -- Intelligence gathering and analysis

1. How Social Media is used by criminals to organize, recruit and plan
2. Big Data ETL API for extracting social media data
3. Text, image, meta data and video
4. Sentiment analysis from social media feed
5. Contextual and non-contextual filtering of social media feed
6. Social Media Dashboard to integrate diverse social media
7. Automated profiling of social media profile
8. Live demo of each analytic will be given through Treeminer Tool

Big Data Analytics in image processing and video feeds

1. Image Storage techniques in Big Data -- Storage solution for data exceeding petabytes
2. LTFS (Linear Tape File System) and LTO (Linear Tape Open)
3. GPFS-LTFS (General Parallel File System -  Linear Tape File System) -- layered storage solution for Big image data
4. Fundamentals of image analytics
5. Object recognition
6. Image segmentation
7. Motion tracking
8. 3-D image reconstruction

Biometrics, DNA and Next Generation Identification Programs

1. Beyond fingerprinting and facial recognition
2. Speech recognition, keystroke (analyzing a users typing pattern) and CODIS (combined DNA Index System)
3. Beyond DNA matching: using forensic DNA phenotyping to construct a face from DNA samples

Big Data Dashboard for quick accessibility of diverse data and display:

1. Integration of existing application platform with Big Data Dashboard
2. Big Data management
3. Case Study of Big Data Dashboard: Tableau and Pentaho
4. Use Big Data app to push location based services in Govt.
5. Tracking system and management

Day 05

How to justify Big Data BI implementation within an organization:

1. Defining the ROI (Return on Investment) for implementing Big Data
2. Case studies for saving Analyst Time in collection and preparation of Data – increasing productivity
3. Revenue gain from lower database licensing cost
4. Revenue gain from location based services
5. Cost savings from fraud prevention
6. An integrated spreadsheet approach for calculating approximate expenses vs. Revenue gain/savings from Big Data implementation.

Step by Step procedure for replacing a legacy data system with a Big Data System

1. Big Data Migration Roadmap
2. What critical information is needed before architecting a Big Data system?
3. What are the different ways for calculating Volume, Velocity, Variety and Veracity of data
4. How to estimate data growth
5. Case studies

Review of Big Data Vendors and review of their products.

1. Accenture
2. APTEAN (Formerly CDC Software)
3. Cisco Systems
4. Cloudera
5. Dell
6. EMC
7. GoodData Corporation
8. Guavus
9. Hitachi Data Systems
10. Hortonworks
11. HP
12. IBM
13. Informatica
14. Intel
15. Jaspersoft
16. Microsoft
17. MongoDB (Formerly 10Gen)
18. MU Sigma
19. Netapp
20. Opera Solutions
21. Oracle
22. Pentaho
23. Platfora
24. Qliktech
25. Quantum
26. Rackspace
27. Revolution Analytics
28. Salesforce
29. SAP
30. SAS Institute
31. Sisense
32. Software AG/Terracotta
33. Soft10 Automation
34. Splunk
35. Sqrrl
36. Supermicro
37. Tableau Software
38. Teradata
39. Think Big Analytics
40. Tidemark Systems
41. Treeminer
42. VMware (Part of EMC)

Q/A session