Agenda

Breakfast Keynote: State-of-the-art Business Applications of Data & Text Analytics

Presented by Pavel Anaschenko, Megaputer Intelligence

Over breakfast, attendees will learn about the latest trends in data and text analytics.

Overview of new capabilities of PolyAnalyst™ and Megaputer

Presented by Brian Howard, Megaputer Intelligence

New capabilities leads to new opportunities. This session highlights the cutting edge advances Megaputer has made over the past year.

Computational Linguistics for Advanced Text Analytics

Presented by Sergei Ananyan, Megaputer Intelligence

This presentation goes beyond the basics of Text Analytics by taking an in-depth look at Computational Linguistics, the bones of text analysis. Attendees will learn how understanding Computational Linguistics increases the accuracy of analysis, creating richer data and leading to better business discoveries.

Morning Break / Networking

Refreshments will be provided.

Hearing the VoC—Call Center Transcripts and Customer Survey Analysis

Presented by Brian Howard, Megaputer Intelligence

Text analysis fills in the gaps of typical survey analysis to provide new insights. This session will discuss how companies can get the most out of VoC data through text analytics.

PolyAnalyst™ Demo Project: Performing Customer Survey Analysis

Presented by Di Cao, Megaputer Intelligence

Using a text analysis tool reveals a greater understanding of customer feedback and product performance to fill in the gaps of typical survey analysis, providing new insights. This session will delve into the details of creating a customer analysis project in Megaputer’s PolyAnalyst tool.

Multi-lingual Capabilities of PolyAnalyst™

Presented by Pavel Anaschenko, Megaputer Intelligence

Analyzing textual data in one language is difficult enough, but analyzing multiple languages is something few software systems have mastered. This session will touch on the different languages PolyAnalyst can analyze.

Guest Speaker: Olga Scrivner, Indiana University, Building Effective Visualization Tools for Everyday Business

Olga Scrivner will be talking about Building Effective Visualization Tools for Everyday Business: Web Reactive Framework

The information age has transformed data into knowledge, that is essential for the well-being of the society, its military, and economic strength. Insights from data and strategic predictions become vital with “unimaginable potential social consequences of development” for science and technology (Borner, 2015). However, with the increasing complexity of data, the transformation from data into actionable knowledge becomes more and more challenging, thus hindering the process of mapping from information to insights. Visual analytics serves as a key to bring value out of data. However, data interpretation and decision-making process are often restricted by the choice of software functionalities.  In addition, there are some technical and programming challenges preventing non-technical users from the access to analytical applications. In this talk, we will share our development of smart visualization for data analytics. To meet users’ needs, the visualization tools should entail a meaningful dialogue between a user and a computer. Furthermore, this interaction should be responsive to users’ specific needs ranging from data specification and view manipulation to data sharing (Heer and Schneiderman, 2012). WVF and Shiny are two applications that enable such an interactivity via reactive framework. In contrast to previous analytical tools, the web-based interactive applications are based on a customer-driven design and offer a user-friendly interface. In addition, the interoperability of our applications is inherent into their back-end structure, that can also be embedded into other applications. Finally, we are able to extend these applications to everyday non-technical users, by developing customizable dashboards and data visualization templates.

New PolyAnalyst™ Web Reports

Presented by Sharon Zhu, Megaputer Intelligence

Megaputer is excited to roll out its new Web Report Platform. This session will demonstrate the features and interface of the new Web Report Platform.

How-to-Guide: Multi-lingual Text Analysis in PolyAnalyst™

Presented by Jeffrey Palan, Megaputer Intelligence

Analyzing data comprised of multiple languages is a difficult task. This How-to-Guide will demonstrate how PolyAnalyst can automatically classify textual data into particular languages, allowing companies to combine analysis outputs from multiple languages.

Employee Survey Analysis

Presented by Brian Howard, Megaputer Intelligence

Maintaining an engaged, productive workforce is vital to a company’s success. This presentation will discuss how text analysis of employee surveys can provide an organization with a wealth of local and global insights concerning employee satisfaction and internal and external issues.

Demo Project: How to Build PolyAnalyst Web Reports

Presented by Sergei Ananyan

Practical Applications of Medical Ontologies in PolyAnalyst™

Presented by Ankit Shah, Megaputer Intelligence

This session will cover how medical ontologies can be used in PolyAnalyst to enhance the accuracy of medical record classification and the efficiency of coding adverse events.

Lunch Break / Networking

Lunch will be provided to conference attendees, which gives Megaputer Analytics Conference attendees the chance to mingle and make new friends.

Social Media analysis: What is Trending for You?

Presented by Margaret Glide, Megaputer Intelligence

This presentation will highlight the use of data and text analysis to monitor Facebook, Twitter, and social news sources and how companies can gain useful insights.

Overview: Text Analysis capabilities of PolyAnalyst™

Presented by Chris Farris, Megaputer Intelligence

Whether a veteran or first time user of PolyAnalyst, attendees will come away with a better understanding of how to analyze textual data.

Overview: Machine Learning Tools of PolyAnalyst™

Presented by Yi Wang, Megaputer Intelligence

This presentation will go over different machine learning tools and techniques PolyAnalyst offers.

Guest Speaker: Brion Scheidel, MaritzCX, PolyAnalyst Tricks, Tips and Gotchas, You Won’t Find in the Help

PolyAnalyst™ is a complex and comprehensive tool and while Megaputer does its best to keep the Help up to date, it’s an impossible challenge to document everything. This session will cover a broad variety of some of the thorny issues we’ve discovered over the years, and the approaches we’ve developed for dealing with many of them.

PDL: Pattern Definition Language for Building Precise Queries

Presented by Chris Farris, Megaputer Intelligence

Learning how to proficiently use PDL, PolyAnalyst’s proprietary search query syntax, will greatly help users harness the power of PolyAnalyst’s text mining capabilities. This session will highlight techniques for creating better search queries in PolyAnalyst.

Solving Classification Tasks with PolyAnalyst™

Presented by Jason Liu, Megaputer Intelligence

This session will highlight all the available classification tools for structured and unstructured data in PolyAnalyst™.

Case Management system: Efficient Handling of Results of Analysis

Presented by Bipin Inamdar, Megaputer Intelligence

This session will feature a Case Management System Megaputer built to deliver analysis outputs in an easy-to-use format for business managers. The solution employs a combination of innovative techniques to analyze and score textual messages against communication and professionalism criteria defined by a company.

Best Practices for Setting a PDL Taxonomy for Employee Survey Analysis

Presented by Jeff Palan, Megaputer Intelligence

This session will cover how users can build PDL taxonomies to effectively analyze employee surveys.

Clustering Techniques of PolyAnalyst™

Presented by Di Cao, Megaputer Intelligence

Clustering can be an effective way to group data sets into subsets. This session will explain the different clustering techniques available in PolyAnalyst.

Afternoon Break / Networking

Stretch the legs and grab some refreshments.

Risk Management: Syncing Marketing Materials and Government Regulations

Presented by Jason Liu, Megaputer Intelligence

This presentation will explore how companies can mitigate risk by using text analytics to create marketing materials that synchronize with government regulations.

New in PDL: Recognizing Document Structure and Information Extraction from Tables

Presented by Yi Wang, Megaputer Intelligence

This session will explore new features and capabilities of PolyAnalyst’s PDL.

Statistical & Distribution Analysis Tools

Presented by Min Chen, Megaputer Intelligence

Structured data analysis involves the development of statistical models based on numbers, dates, and categories. This session will explore the different capabilities PolyAnalyst has, such as: finding associations, numerical modeling, anomaly detection, time series, etc.

Guest Speaker: Eric Wen Su, Lilly, Systematic Drug Repositioning Using Text Mining Tools on ClinicalTrials.gov

Lilly’s Principal Research Scientist, Eric Wen Su, will be delivering a guest presentation on the topic of Text mining tools in Pharma.

Drug repositioning (i.e., drug repurposing) is the process of discovering new uses for marketed drugs. Historically, such discoveries were serendipitous. However, the rapid growth in electronic clinical data and text mining tools makes it feasible to systematically identify drugs with the potential to be repurposed. Described here is a novel method of drug repositioning by mining ClinicalTrials.gov. Text mining tools extracts “Serious Adverse Events” (SAE) data from randomized trials in ClinicalTrials.gov. Through a statistical algorithm, a workflow ranks the drugs where the treatment arm has fewer predefined SAEs than the control arm, indicating that potentially the drug is reducing the level of SAE. Hypotheses could then be generated for the new use of these drugs based on the predefined SAE that is indicative of disease (for example, cancer).

XPDL: New Language for Accurate Information Extraction and Text Coding

Presented by Margaret Glide, Megaputer Intelligence

XPDL was created so that users could easily create custom entities to extract important information. This session will demonstrate how users can get the most out of PolyAnalyst’s XPDL function.

Using GIS module of PolyAnalyst™

Presented by Wilson Zhou, Megaputer Intelligence

This session will go into the the techniques and applications of PolyAnalyst’s GIS module.

Text Analysis of EMRs for Identifying Opportunities and Risks

Presented by Ankit Shah, Megaputer Intelligence

This presentation will explore the different types of opportunities and risks that can be extracted automatically from EMRs by text analysis systems.

PolyAnalyst™ Demo Project: Automating Competitive Intelligence

Presented by Sergei Ananyan, Megaputer Intelligence

This demo will go through the steps of how an Automated Competitive Intelligence Solution was created, as well as describe the real life benefits.

PolyAnalyst™ Scheduler and Integration with External Systems

Presented by Bipin Inamdar, Megaputer Intelligence

Once a project has been setup in PolyAnalyst, users can save time and automate reporting by using the Scheduler feature. This session will walk through how to use PolyAnalyst’s Scheduler and how it can be integrated with external systems.

ACTIVITY: Dinner / The Irish Lion

Dinner begins at 6:30 PM, please refer to your Conference Kit for menu options and prepare a dinner card. This venue is a short walk from the Monroe Convention Center. Please join us at:

Extracting Entities and Relationships from Financial, Legal and Medical Documents

Presented by Ankit Shah, Megaputer Intelligence

This presentation will explore the different types of entities and relationships that can be automatically extracted out of medical records, reports, and legal documents by text analysis systems and discuss customized entity extraction techniques for domain-specific knowledge targeting.

INSURANCE: Improving Subrogation Prediction Through Text Analytics

Presented by Chris Farris, Megaputer Intelligence

This presentation will present the key objectives and benefits of an automated solution that analyzes insurance claims and predicts likely subrogation recovery opportunities.

PolyAnalyst™ Ontologies and Other Resources

Presented by Yilong Jia, Megaputer Intelligence

This session will cover the resources users have at their disposal in PolyAnalyst.

Automating Competitive Intelligence

Presented by Sergei Ananyan, Megaputer Intelligence

As the competitive landscape changes constantly, automated text analysis systems equip businesses with in-depth analysis of open sources (articles, corporate reports, and press releases) to monitor the business activities of competitors, reveal emerging customer needs, and identify new market trends and promising technologies. This presentation will highlight the key objectives, challenges, technologies, and results provided by a modern competitive intelligence solution.

INSURANCE: Entity Resolution Applications in Insurance Claims Analytics

Presented by Ankit Shah, Megaputer Intelligence

This session will highlight the benefits of different entity extraction applications in insurance claim notes.

PolyAnalyst™ Ontologies and Other Resources

Presented by Yilong Jia, Megaputer Intelligence

This session will cover the resources users have at their disposal in PolyAnalyst.

Semi-Supervised Learning and Its Application

Presented by Mohsen Sayyadiharikandeh
Computer Science, Indiana University

Machine learning has shown its effectiveness in lots of scientific and business projects. In order to teach the machine to learn a model from huge amount of data sources we need to have labeled data which is expensive to make and laborious and time-consuming task while unlabeled data is everywhere. Supervised learning methods relied on fully annotated data sets which are first option to be used in prediction tasks. But there have been some techniques to learn from both labeled and unlabeled data known as Semi-Supervised Learning(SSL) methods. In this presentation we will review some famous SSL methods and its applications. We analyze the results of applying SSL methods on wikipedia to see its performance.

INSURANCE: Fraud Detection in P&C Insurance

Presented by Min Chen, Megaputer Intelligence

Automated data analysis systems have become a valuable fraud detection tool for insurance companies, particularly in detecting anomalies and suspicious activity that is often missed through manual analysis. This presentation will cover Megaputer’s  data and text analysis solution for P&C insurance fraud detection.

Demo Project: Corporate Compliance Monitoring with Text Analytics

Presented by Sergei Ananyan, Megaputer Intelligence

Monitoring corporate compliance can be a challenge. Learn how employing a text analytics solution can help companies monitor compliance at a more effective and efficient rate.

Morning Break / Networking

Morning refreshments will be provided.

Guest Presentation: Professor Fukawa, Consumer Big Data & Innovation in Marketing

Presented by Professor Fukawa, Missouri University of Science & Technology 

More than half of Big Data projects fail. In some of these cases, firms may try to extract insights from consumer Big Data using the same traditional statistical methods as they analyze traditional consumer data. In other cases, firms may rely too much on existing knowledge and theory (i.e., knowledge-based view) in analyzing Big Data. However, Big Data, characterized with 3Vs (Volume, Velocity, and Variety), requires unique approaches to analyze and extract insights successfully. Firms may need to focus more on exploring what we don’t know using incomplete information and unstructured data (i.e., ignorance-based view), instead of enhancing what we know using complete information and structured data (i.e., knowledge-based view). As an illustrative example, we discuss how PolyAnalyst software can be successfully utilized to enhance ignorance-based view and extract consumer insights from Social Media, such as Yelp. Overall, my presentation addresses the following questions:
· Why do many Big Data projects fail to achieve their goals?
· How does consumer Big Data force firms to transform their marketing activities and their organizations?
· How does consumer Big Data force marketing researchers to transform the way we understand consumers?
· Why do companies fail to achieve nonlinear innovation with consumer insights derived from Big Data?
· How does ignorance-based view (vs. knowledge-based view) enable firms to utilize consumer Big Data and achieve innovation in a hyper-competitive marketplace?
· How does PolyAnalyst software support ignorance-based view?

INSURANCE: Fraud Detection in Healthcare Insurance

Presented by Min Chen, Megaputer Intelligence

Automated data analysis systems have become a valuable fraud detection tool for healthcare insurance companies, particularly in detecting anomalies and suspicious activity that is often missed through manual analysis. This presentation will highlight a study involving the implementation of data and text analysis for healthcare insurance fraud detection.

Sentiment Analysis with PolyAnalyst™

Presented by Di Cao, Megaputer Intelligence

This session will tackle the difficulties of identifying sentiment in textual data by detailing solutions Megaputer’s analysts have employed.

SPEAKER PANEL: TBA

INSURANCE: Warranty Claims Analysis—Fraud Detection

Presented by Zhen Li, Megaputer Intelligence

Automated data analysis systems have become a valuable fraud detection tool for insurance companies, particularly in detecting anomalies and suspicious activity that is often missed through manual analysis of claim notes. This presentation will highlight a case study involving the implementation of data and text analysis for insurance fraud detection of claim notes.

Entity Resolution: Challenges, Ideas, and Implementations

Presented by Sergei Ananyan, Megaputer Intelligence

By addressing the challenges and presenting new ideas and implementation areas, this session will uncover the underlying value of a powerful entity resolution feature.

PHARMA & LIFE SCIENCES: Challenges in Setting Up a Text Analysis Solution for a Pharma Company

Presented by Yi Wang, Megaputer Intelligence

Having experience the challenges of setting up a text analysis solution for a pharma company first hand, Brian Howard will outline the challenges that can arise and how these challenges can be overcome.

INSURANCE: Analyzing External Sources—Detecting Emerging Trends (NHTSA)

Presented by Sergei Ananyan, Megaputer Intelligence

This session will explore how public data from the National Highway Traffic Safety Administration (NHTSA) can be used to detect emerging issues in automobiles that led to vehicle recalls and discuss how text analysis systems can be used to predict potential recalls and issues earlier in the process.

PolyAnalyst™ Demo Project: Detecting Voters Fraud

Presented by Chris Farris, Megaputer Intelligence

This demo will provide a close look at how a solution was developed in PolyAnalyst to detect voter fraud on a State level.

Lunch Break / Networking

Lunch will be provided to conference attendees, giving attendees the chance to mingle and make new friends.

PHARMA & LIFE SCIENCES: Research Literature—Extracting entities, relations and emerging trends

Presented by Yilong Jia, Megaputer

This presentation gives an overview of biomedical entities and features. Attendees will learn how text analysis techniques can help researchers perform literature summaries, data management, knowledge discovery, experimental design, and predictive modeling.

HEALTHCARE: Can Medical Coding of EMRs be Automated?

Presented by Ankit Shah, Megaputer Intelligence

This presentation will outline the difficulties of creating an automated medical coding system and how Megaputer overcame the challenge to create a robust solution.

Social Network Analysis: Tasks, Techniques and Applications

Presented by Sergei Ananyan, Megaputer Intelligence

This session will demonstrate how to identify applications, create the right project, and utilize efficient techniques to implement social network analysis in healthcare.

PHARMA & LIFE SCIENCES Featured Presentation: Identifying Customer Needs from Their Point of View/Case study for Analytics

Presented by Valerie Brown, Eli Lilly & Company

Being trustworthy, easy to work with, and making customers feel cared for at every turn are the core values for Eli Lilly and Company. How do we use data to illustrate how we meet are core values with customers? What do we need to do differently? It is all about the data. What can we learn about our customers? What can we learn from our customers? How can we use insights gained from the data to engage customers? How do we use insights to improve the customer experience? This presentation will:

1. Describe how data from T2i (Transaction to interaction) is employed by one business unit to identify customer centric insights.
2. Analyze data through the perspective of the organization’s core values.
3. Identify how to make the customer experience better.

HEALTHCARE: Performing Audit of Manual EMR Coding Results

Presented by Nick Hotz, Megaputer Intelligence

This session will cover how to audit manual EMR coding results in PolyAnalyst.

PolyAnalyst™ Demo Project: Finding Most Influential Medical Researchers

Presented by Yilong Jia, Megaputer Intelligence

Public research resources and databases such as PubMed offer valuable and up-to-date information on various biomedical and pharmaceutical scientific fields. This demo details how finding influential medical researchers can be automated through text analysis in PolyAnalyst.

PHARMA & LIFE SCIENCES: Research Literature—Identifying Influential Researchers by Topic

Presented by Yilong Jia, Megaputer Intelligence

Public research resources and databases such as PubMed offer valuable and up-to-date information on various biomedical and pharmaceutical scientific fields. This presentation explores a variety of public biomedical research resources and demonstrates how identifying influential researchers by topic can be automatically extracted from text-based sources.

HEALTHCARE: Extracting and Interpreting Clinical Findings

Presented by Ankit Shah, Megaputer Intelligence

Healthcare professionals benefit by having a system that automatically extracts clinical findings, but a system that goes one step further, and interprets clinical findings, is indispensable. This presentation will describe such a system.

Integrating Analytics with a Case Management System

Presented by Bipin Inamdar, Megaputer Intelligence

This session outlines how integrating analytics into a case management system can drastically increase the benefits for end users.

Afternoon Break / Networking

Stretch the legs and grab some refreshments.

PHARMA & LIFE SCIENCES: Industry Standard Resources for Pharma Text Analytics

Presented by Yi Wang, Megaputer Intelligence

A streamlined text analysis solution can greatly help identify and track medical issues from the patients and doctors to the insurance, pharmaceutical, and regulatory agencies that all apply different standards to describe the same event. This presentation will cover the challenges of adverse event reporting and issues related to translating information to multiple medical vocabularies and coding structures.

HEALTHCARE: Are You Compliant? Analysis of Compliance Line Records

Presented by Zhen Li, Megaputer Intelligence

Complying with hundreds of regulations can be challenging. This presentation will educate healthcare professionals on how employing a text analytics solution can ensure compliance.

Working with BIG DATA: Introducing PolyAnalyst™ for Hadoop

Presented by Pavel Anaschenko, Megaputer Intelligence

This presentation will discuss how data and text analysis systems can adapt to handle such large data sets, and provide an overview of best practices for performing text analysis on a BIG scale.

PHARMA & LIFE SCIENCES: Pharmacovigilance— Key Challenges and Solutions

Presented by Jason Liu, Megaputer Intelligence

To comply with federal drug safety guidelines, pharmaceutical manufacturers must read and process a flood of drug safety reports to extract actionable information. This session presents a pharmacovigilance solution for computer-assisted decision-making and case management.

HEALTHCARE: Lessons Learned from Patient Safety Report Analysis

Presented by Jeffrey Palan, Megaputer Intelligence

This presentation will highlight the lessons Megaputer has learned from analyzing patient safety data, and how companies can benefit from an automated text analysis solution.

HCI/UIX: How Megaputer Designs Software

Presented by Sharon Zhu, Megaputer Intelligence

During this presentation, attendees will learn how Megaputer designs data and text analytics software. Specific design examples, that went all the way from a prototype to implementation, will be walked through in detail.

PHARMA & LIFE SCIENCES: Medical Device Repair Notes Analysis

Presented by Chris Farris, Megaputer Intelligence

To ensure safe and reliable function of medical devices and diagnostic instruments, these intricate devices often require routine maintenance and repairs. This session presents how an emerging issue detection solution was implemented at a large biotech company.

HEALTHCARE GUEST SPEAKER: Amanda Dawson, PhD, Select Medical, Approaches to Using NLP Results in Healthcare Analytics

Presented by Dr. Amanda Dawson, Select Medical

Information to Come

PolyAnalyst™ Roadmap for 2018-2019

Presented by Pavel Anaschenko, Megaputer Intelligence

Find out where Megaputer is focusing its efforts in the ever changing world of data and text analytics.

Activity: Dinner / Malibu Grill

Dinner begins at 6:30 pm. Entree options are available in your Conference Kit. Please join us for dinner at:

Malibu Grill
106 N Walnut St
Bloomington, IN 47404
812-332-4334

Website

How Text Analytics Works?

Presented by Sergei Ananyan, Megaputer Intelligence

This presentation strips down a robust text analytics system to the nuts and bolts to explain exactly how a machine can understand human language.

Data Cleansing & Management, Dictionaries in PolyAnalyst™

Presented by Ankit Shah, Megaputer Intelligence

This workshop will teach users how to generate a clean data set by using PolyAnalyst’s spellcheck and dictionary features.

Document Classification with PolyAnalyst™- Part 1

Presented by Chris Farris, Megaputer Intelligence

Part 1 will cover the steps users must take to ensure accurate classification.

Techniques for Automated Extraction of Entities and Relationships from Documents

Presented by Yilong Jia, Megaputer Intelligence

This workshop will cover the different techniques PolyAnalyst users can employ to extract entities and relationships from documents.

Lunch Break

Document Classification with PolyAnalyst™- Part 2

Presented by Jason Liu, Megaputer Intelligence

Document Classification in PolyAnalyst Part 2 will pick up from the foundation laid in Part 1- teaching users how to correctly classify documents in an efficient manner.

Working with Diverse Data Sources and Languages in PolyAnalyst™

Presented by Jeffrey Palan, Megaputer Intelligence

For users who work with multiple data sources or languages in PolyAnalyst, this workshop will provide the knowledge needed to successfully analyze diverse data sets.

Text Analysis with PolyAnalyst™- Best practices

Presented by Zhen Li, Megaputer Intelligence

With so many different text analysis functions and solutions available in PolyAnalyst, this workshop will help users refine their analysis skills.

Detailed Overview of the Subrogation Prediction Solution

Presented by Chris Farris, Megaputer Intelligence

This presentation will walk through the different steps of a data analysis project involving subrogation prediction. You will learn an overview of the techniques involved in building this solution in PolyAnalyst.