Sales of Orthopedic Equipment
Xiaomeng (Mina) Chai
11/25/2014
Client’s Background
• Client:
a large manufacturer of orthopedic
equipment in the United States
• Customer base:
almost all hospitals over the 50 states
Client’s Products
• Orthopedic parts and equipment
• Medications administered in the process of
surgery, rehabilitation, and recovery
The Company Thinks …
• SALES!
– High sales
– Moderate sales (further sales potential)
– Little or no sales (substantial potential gain)
Imagine …
We think…
• ORTHOPEDIC ACTIVITIES!
– Small general hospitals (little or no interest)
– Large general hospitals (moderate interest)
– Specialized hospitals (main target group!)
Objective
• Increase sales...
…in the more desirable groups!
• How?
– Identify target hospitals
– Study them individually
• Another objective: other ways to classify
hospitals?
Dataset
All U.S. hospitals are in the dataset:
Variables
A subset of variables is already selected
Variables
Methodology
• Data Mining
– Dimension Reduction
• Factor Analysis
• Principal Component Analysis
– Cluster Analysis
• Hierarchical Clustering
• Centroid Methods
• Regression analysis
Data Mining
• Overall goal—to extract information from a data set and
transform it into an understandable structure for further
use. (Wikipedia)
• The objective of data mining is to identify nuggets, small
clusters of observations in these data that contain
unexpected, yet potentially valuable, information. (The
author)
Data Mining
Approach to data mining
1. Dimension (variable) reduction
– Principle components
– Factor analysis
1. Data segmentation and selection
– Cluster analysis
– Tree methods
– Neural nets
1. Data analysis of interesting segments
This case study
PART 1:Select Market Segments
• Find state or group of states (at least 300 hospitals)
– IL, IN, MI, WI are selected (590 hospitals)
Transformation
Log or square root transformations are performed
Transformation
Before After
so far…
Dimension Reduction
• Two stages factor analysis
– Operational factor (HIP95, KNEE95, HIP96, KNEE96,
and FEMUR96)
– Size factor (BEDS, OUTV, ADM, SIR, TH, and TRAUMA)
and rehab factor (RBEDS and REHAB)
Factor Analysis--stage1
Factor Analysis—stage2
Factor Analysis: Rotate?
• More interpretable results.
• Orthogonal rotation methods (VARIMAX) is commonly
used.
e.g. Look at variable X33 here:
Factor Analysis—stage2
Principal Component Analysis--stage 1
Principal Component Analysis--stage 2
R
Factor Analysis in R
Factor Analysis in R
Factor Analysis in R
PCA in R
PCA in R
PCA in R
PCA in R
PCA in R
Factor Analysis
13 variables are divided into 3 factors:
Textbook Question:
Graph the main principal components. Are there any visible clusters?
The banding is relatively vertical, REHAB is affecting factor 2 (RBEDS and REHAB).
so far…
Cluster Analysis
• To determine the best cluster to concentrate on
for improving sales.
• Two popular methods
– Hierarchical Clustering (interpoint distance)
• Single linkage
• Average linkage
• Ward
– Centroid Methods
• K-means algorithm
• Partitioning Around Medoids (PAM)
Cluster Analysis
• Hierarchical Clustering:
1. Start with a cluster at each sample point
2. At each stage of building the tree the two closest clusters joint
to form a new cluster
Cluster Analysis
• Centroid Methods (K-means algorithm)
1. K seed points are chosen and the data is distributed
among k cluster
2. At each step, switch a point from one cluster to
another if the R2
is increased
3. Clusters are slowly optimized by switching points
until no improvement of the R2
is possible
Cluster Analysis
• Centroid Methods (K-means algorithm)
Cluster Analysis
• Partitioning Around Medoids (PAM)
1. Search for k representative medoids
2. K clusters are constructed by assigning each point
to the nearest medoid
3. The goal is to find k medoids which minimize the
sum of the dissimilarities of the observations to their
closest representative medoid.
Cluster Analysis
• PAM VS K-means
– PAM operates on the dissimilarity matrix
– PAM minimizes a sum of dissimilarities instead of a
sum of squared Euclidean distances
– Silhouette plot (select the optimal number of clusters)
Cluster Analysis
• To determine the best cluster to concentrate on
for improving sales.
• Two popular methods
– Hierarchical Clustering (interpoint distance)
• Single linkage
• Average linkage
• Ward
– Centroid Methods
• K-means algorithm
• Partitioning Around Medoids (PAM)
Cluster Analysis
…
…
Cluster Tree
PAM in R
PAM in R
• Silhouette width:
si=(bi-ai)/max(ai,bi)
Large Si (almost 1) are very well clustered
PAM in R
Cluster Analysis
Cluster Analysis
Cluster Analysis in R
Cluster of Interest
so far…
Part 2-Estimate Potential Sales
• Part1 – Select Market Segments : DONE
• Part2 – Estimate Potential Sales
Regression Analysis
Regression Analysis
Regression Analysis
• Hospitals with large negative residuals:
HID CITY STATE RESIDUAL Gain
087043 Chicago IL -2.8766 68.590
915042 South Bend IN -1.7989 16.440
016045 Beloit WI -2.5633 24.893
020042 Columbus IN -2.5146 34.710
078045 Madison WI -2.2309 59.362
109043 Chicago IL -1.9317 47.980
262043 Peoria IL -2.5952 90.593
Thank you and Happy Holiday!

Data Mining Case Study

Editor's Notes

  • #4 Orthopedic equipment refers to a variety of structural devices designed to stabilize, protect, and/or correct orthopedic disorders. Common medications used to treat orthopedic conditions include nonsteroidal anti-inflammatory medications (e.g. Motrin, Aleve, Naprosyn, Celebrex), Glucosamine, and others.
  • #5 From the point of view of sales
  • #7 From the point of view of activities
  • #9 4703 hospitals and 19 variables Chicago has 45 hospitals
  • #16 From raw data to small dataset
  • #18 Independent var—linear trend Dependent var--normality
  • #24 The elements of the Factor Pattern reflect the unique variance each factor contributes to the variance of an observed variable. The reason factor analysis is not stopped after this initial factoring stage, without rotating the factors, is that the factors as they currently exist are not easily interpretable. In an ideal solution, the variables should “load” highly (have a high value that approaches 1) on just one factor each.
  • #25 Final Conmmunality Estimates: It can be derived by taking sum of squares of each row of the factor pattern. This is the variance of the observed variable that is accounted for by each factor.  
  • #34 The left and bottom axes are showing the loadings; the top and right axes are showing principal component scores. meaningful visual representation of the structure of cases and variables.
  • #47 Cluster History section starts out with n (590) clusters of size 1 and continues until all the obs are included into one cluster. R^2: the proportion of variance explained by a particular cluster. In the first step, n-1 clusters are formed, R^2 are then computed to have the largest R^2. So the largest R^2 will form the first cluster. Thus, at each step of the algorithm clusters or observations are combined in such a way as to maximize the r2 value. the biggest jump between cluster 5 and 4 with almost 0.1 difference. Therefore, I chose 5 clusters for my future analysis.
  • #50 Put a(i) = average dissimilarity between i and all other points of the cluster to which i belongs (if i is the only observation in its cluster, s(i) := 0 without further calculations). For all other clusters C, put d(i,C)= average dissimilarity of i to all observations of C. The smallest of these d(i,C) is b(i) := \min_C d(i,C), and can be seen as the dissimilarity between i and its “neighbor” cluster, i.e., the nearest one to which it does not belong. Finally,