Page 53 -

52 Part I • Decision Making and Analytics: An Overview

Application Case 1.3

Analysis at the Speed of Thought
Kaleida Health, the largest healthcare provider in other hospitals across the country. Comparisons are
western New York, has more than 10,000 employ- made on various aspects, such as length of patient
ees, five hospitals, a number of clinics and nursing stay, hospital practices, market share, and partner-
homes, and a visiting-nurse association that deals ships with doctors.
with millions of patient records. Kaleida’s traditional
reporting tools were inadequate to handle the grow- Questions for Discussion
ing data, and they were faced with the challenge of 1. What are the desired functionalities of a report-
finding a business intelligence tool that could handle ing tool?
large data sets effortlessly, quickly, and with a much 2. What advantages were derived by using a report-
deeper analytic capability. ing tool in the case?
At Kaleida, many of the calculations are now
done in Tableau, primarily pulling the data from
Oracle databases into Excel and importing the What We can Learn from this application
data into Tableau. For many of the monthly ana- case
lytic reports, data is directly extracted into Tableau Correct selection of a reporting tool is extremely
from the data warehouse; many of the data queries important, especially if an organization wants to
are saved and rerun, resulting in time savings when derive value from reporting. The generated reports
dealing with millions of records—each having more and visualizations should be easily discernible; they
than 40 fields per record. Besides speed, Kaleida should help people in different sectors make sense
also uses Tableau to merge different tables for gen- out of the reports, identify the problematic areas,
erating extracts. and contribute toward improving them. Many future
Using Tableau, Kaleida can analyze emergency organizations will require reporting analytic tools
room data to determine the number of patients who that are fast and capable of handling huge amounts
visit more than 10 times a year. The data often reveal of data efficiently to generate desired reports with-
that people frequently use emergency room and out the need for third-party consultants and service
ambulance services inappropriately for stomach- providers. A truly useful reporting tool can exempt
aches, headaches, and fevers. Kaleida can manage organizations from unnecessary expenditure.
resource utilizations—the use and cost of supplies—
which will ultimately lead to efficiency and standard- Source: Tableausoftware.com, “Kaleida Health Finds Efficiencies,
ization of supplies management across the system. Stays Competitive,” tableausoftware.com/learn/stories/user-
Kaleida now has its own business intelligence experience-speed-thought-kaleida-health (accessed February
department and uses Tableau to compare itself to 2013).

predictive analytics
Predictive analytics aims to determine what is likely to happen in the future. This analy-
sis is based on statistical techniques as well as other more recently developed techniques
that fall under the general category of data mining. The goal of these techniques is to be
able to predict if the customer is likely to switch to a competitor (“churn”), what the cus-
tomer is likely to buy next and how much, what promotion a customer would respond
to, or whether this customer is a creditworthy risk. A number of techniques are used in
developing predictive analytical applications, including various classification algorithms.
For example, as described in Chapters 5 and 6, we can use classification techniques such
as decision tree models and neural networks to predict how well a motion picture will
do at the box office. We can also use clustering algorithms for segmenting customers
into different clusters to be able to target specific promotions to them. Finally, we can

M01_SHAR9209_10_PIE_C01.indd 52 1/25/14 7:46 AM