Texas A&M / SAS® Analytics Forum at Houston CityCentre

Hosted by the Mays Business School at Texas A&M University in Houston, TX

Register Here:

Where
CityCentre Three 842 W Sam Houston Pkwy North, Suite 200
Houston, TX 77024
(979) 845-6855

Select slides will be available after the event.

Event Details

Date: January 31, 2019 from 8:30 am to 3:00 p.m. CST

Location: Houston, TX - CityCentre Three, Suite 200 (Texas A&M University-Mays Business School facility)

Cost: There is no cost to attend this event

Texas A&M SAS Analytics Forum

An event hosted by the Mays Business School at Texas A&M University. This event will highlight speakers from the SAS Institute, Inc. and industry experts that will discuss topics including analytics and data mining to make better business decisions. A panel of experts from industry will discuss how their companies are using big data and analytics, and how they are fostering a fact-based decision making culture in their companies. The number of participants is limited.

Participants will hear how big data and analytics are being used in companies in:

• Energy Analytics
• Healthcare Analytics
• Sports Analytics

Participants also gain insight into:

• The benefits from using big data and analytics in your business
• Common obstacles to big data and analytics
• How companies build a culture of using big data for better decision making
• The types of data, software and statistical methods used in analytics decision making

Reserve your seat any time before January 31st. Dress is business casual. Continental breakfast and light lunch will be available free of charge.

Tentative Agenda

• Registration, exhibitor set-up, networking, and breakfast: 8:15 a.m.- 8:45 a.m.

• A sessions: 9:00 a.m. - 10:00 a.m.
Pick one:
• Healthcare Analytics
• Energy Analytics

• Break and Transition: 10:00 a.m. - 10:15 a.m.

• B Sessions: 10:15 a.m. - 11:15 a.m.
Pick one:
• Healthcare Analytics
• Oil and Gas Analytics

• Lunch with Keynote - Sports Analytics: 11:15 a.m. - 12:30 p.m.

• C Sessions: 12:45 a.m. - 1:45 p.m.
Pick one:
• Deep Learning
• Mobility Index

• Time with exhibitors and networking: 1:45 p.m. - 3:00 p.m.

• Adjourn: 3:00 p.m.

Limited exhibitor opportunities are available. Please contact us to inquire.

Keynote Speaker

William Wash

William Wash has been a marketing technologist for over 20 years in a number of industries. He has brought his knowledge and passion to the Internet of Things division at the analytics leader SAS. Since joining he has been focused on the human side of IoT, how people interact with that technology and how they can use that connectivity to improve their lives. He has been engaged with international retailers, gaming and hospitality giants, and professional sports teams to optimize what their staff, customers, guests, fans, and players experience. When architecting these solutions William brings to bear his wealth of experience with cutting edge enterprise and open source big data, analytics, streaming, and decisioning platforms.

Abstract
How professional sports teams and leagues are leveraging data across sports and business operations.

Featured Speakers

Mark J. Konya, P.E.

Mark Konya, Principal Industry Consultant in the Global Energy Practice at SAS, earned graduate degrees at Washington University and University of Illinois. With over 35 years of utility experience in power generation, distribution engineering, process improvement, and leading customer analytics initiatives, Mark shares his insights and expertise with customers on analytics strategies and deriving value from analytics initiatives. Mark is a member of IEEE/PES, a licensed professional engineer, a Six Sigma Black Belt and a certified Lean facilitator.

Abstract:
Disruptions in the energy supply chain continue to challenge the viability of traditional utility business models. For example, some utilities with declining load growths – due to distributed energy resources and energy efficiency programs – are in financial trouble. Such disruptors erode revenue and ultimately could sound the death knell for some companies that traditionally make money based on their capital investments and the volume of electricity they sell. In response to disruptions in the electric energy sector, modern energy suppliers have emerged. Thanks to data from the Internet of Things (IoT), advanced analytics and artificial intelligence (AI), both new and existing suppliers are adapting to – and even thriving in – the quickly changing energy supply landscape. This session will spotlight significant disruptions to the energy supply chain and how modern energy suppliers can leverage advanced analytics to ensure long-term survival in a chaotic marketplace.

Abiodun Akogun

Abiodun Akogun, has a successful track record of using data analytics and technology to solve key business problems and how technology can be used to improve existing business processes. He graduated from the University of Ife (now Obafemi Awolowo Univeristy) with a B.S. in Electrical Engineering. He holds graduate degrees in Electrical Engineering from Tennessee Technological University, and a Master's in Analytics from Texas A&M University, College Station. His focus is how analytics can be used to gain competitive advantage. He has extensive experience using Big Data Analytics tools (R, SAS, JMP, Tableau, MicroStrategy, SQL, Hadoop-HDFS, Hive, Sqoop, Flume, Kafka, SparkSQL and Python-Tensorflow). He has worked on use cases in different verticals such as telecommunications, retail and health care.

Abstract:
Length of stay is defined as the number of days from initial admit to the date a patient is discharged from a given hospital facility. It describes a single episode of hospitalization. Medicaid through its Bundled Payments for care Improvement (BPCI) initiative pays a flat fee for a single episode of patient hospitalization. Hospitals thus want to reduce LOS for such cases. The target audience for this study is Hospital executives, clinical and operation leaders. A key metric associated with length of Stay is Average Length of Stay (ALOS). ALOS is calculated by dividing the sum of impatient days by the number of patient admissions within the same diagnostic group. In this study, ALOS was measured as Discharged ALOS. Discharged ALOS is calculated by dividing the total patient days by the number of patients in a population (Discharges). We compare ALOS across different metrics across our facilities and provide analytics to analyze and predict LOS per patient across Facilities.

Cody Dufour

Cody Dufour, is an experience process improvement engineer with a demonstrated history of working in the health wellness and fitness industry. Skilled in Salesforce.com Development, Agile Methodologies, (ETL), SQL Servier Management Studio, and Project Management. Cody is on his last semester in the MS Analytics program at Texas A&M University.

Abstract:
This session will begin with an overview of how a healthcare organization utilizes a voluntary e-learning behavioral program to positively impact participant’s health; targeting significant health issues such as obesity, type 2 diabetes, and metabolic syndrome. In consideration of the negative effects of poor population health, reliance on analytics is key to understanding the drivers of engagement in this type of program to increase its effectiveness and scalability. The ability to access data quickly and use analytics to measure success and drive decisions as program curriculum and technology evolves is key to organizational impact and success.

This session will describe a voluntary e-learning behavioral program that uses analytics to understand drivers to positively impact participant’s health; targeting significant health issues such as obesity, type 2 diabetes, and metabolic syndrome.

Ziad Katrib

Ziad Katrib is currently Principal Data Scientist at Foundation3.ai, a Houston startup he co-founded. He focuses on building and deploying AI, as a service for clients in various industries, focusing primarily on industrial applications. Most recently, Ziad served as Director of Operations Analytics at calpine, where he led a cross functional team of data scientists, engineers, and software developers in deploying and developing learning based systems for equipment operations and commercial decisions optimization. Ziad continuously advises executive leadership teams and senior management on operational and commercial growth decisions through data driven insights. Ziad received his Master's in Analytics from Texas A&M and focused on solving business and technical challenges using statistical and machine learning methods. He has spent most of his career applying analytics to achieve commercial excellence. Ziad also received an MBA with a minor in Finance from the University of Texas at Tyler. Before settling down in Houston, he had the opportunity to travel the world with GE as a Gas Turbine engineer and commission Gas Turbines and rotating equipment in the US, India, Sri Lanka and the Middle East.

Abstract:
Deep Learning has seen unparalleled success in Image Recognition, Speech and Audio. It also continues to make headway in industrial applications. However Deep Learning models come with some trade offs, they require extra effort to be deployed in production systems. Data Scientists could be better served by benchmarking the state of the art solution using "shallow" machine learning as a first step. During this talk we will use a real data set to demonstrate the usefulness of baselining prediction accuracy before building a deep learning pipeline.

Yoel Kluk

Yoel Kluk is currently the sub director of strategic planning at KIO Networks. He has an extensive background developing, implementing, and measuring strategic and business planning initiatives and process for Fortune 100 companies and non-profit organizations. Proficient in building organization-wide planning capabilities and knowledge needed to implement strategic planning priorities. Yoel has a Bachelor's in Business Management from the Universidad Panamericana in Mexico and a Master's in Analytics from Texas A&M University. .

Abstract:
When analyzing the complexity of moving people to and from work the amount of data points are great but little has been done to create predictive models to complement the graphic information available. In this session participants will be exposed to a simple model that demonstrates the impact of urban mobility on productivity.
The model includes discovering the weight of variables like comfort and security have on a final mobility index. Then correlating the index with a decision of energy investment at work to finally predicting the effect of transportation on productivity. The project has been recognized by the Inadem (National entrepreneurship institute of Mexico) and is currently being sponsored by UBER to be used as proof of the benefits they have on the economy.

Salsawit (Sasi) Shifarraw

Salsawit (Sasi) Shifarraw works as a Data Scientist at the University of Texas Health Science Center at Houston running risk model analysis. She previously worked as a Lead Application Programmer for Memorial Hermann Health System where she ran ISD Enterprise Analytics and Enterprise Data Warehouse among other other tools. She holds a Master's in Analytics from Texas A&M University.

Abstract:
Length of stay is defined as the number of days from initial admit to the date a patient is discharged from a given hospital facility. It describes a single episode of hospitalization. Medicaid through its Bundled Payments for care Improvement (BPCI) initiative pays a flat fee for a single episode of patient hospitalization. Hospitals thus want to reduce LOS for such cases. The target audience for this study is Hospital executives, clinical and operation leaders. A key metric associated with length of Stay is Average Length of Stay (ALOS). ALOS is calculated by dividing the sum of impatient days by the number of patient admissions within the same diagnostic group. In this study, ALOS was measured as Discharged ALOS. Discharged ALOS is calculated by dividing the total patient days by the number of patients in a population (Discharges). We compare ALOS across different metrics across our facilities and provide analytics to analyze and predict LOS per patient across Facilities. One of challenges with using analytics to drive the benchmarking conversation with clinical and quality leaders is getting past the “our patients are sicker” mentality. The risk adjustment methodology applied when comparing cases is often unsatisfactory to leadership. This occurs in various areas of healthcare data such as drug utilization, cost as well as hospital complication rates.This session will go over examples of some of the methods and limitations in risk adjustment methodologies in healthcare, as well as strategies to overcome the “our patients are sicker” response when presenting your analysis to your audience.