Proactive Career Path Analysis
SAP Predictive Analysis for HR
Henner Schliebs, August 2013
© 2013 SAP AG. All rights reserved. 2Customer
How can we analyze the flow of people with
SAP Predictive Analysis?
1
Visual...
© 2013 SAP AG. All rights reserved. 3
Our Source data is based
on Excel but could also
come via HANA or BO
Universe
© 2013 SAP AG. All rights reserved. 4
© 2013 SAP AG. All rights reserved. 5
© 2013 SAP AG. All rights reserved. 6
Here we can preview
the data that is to be
imported
© 2013 SAP AG. All rights reserved. 7
The imported data contains
information on position changes
as well as master data be...
© 2013 SAP AG. All rights reserved. 8
Our newly created
measures
Aggregation
behavior
© 2013 SAP AG. All rights reserved. 9
Switch aggregation to “average”
to calculate average success
ratio of a position cha...
© 2013 SAP AG. All rights reserved. 10
Let’s rename the
measures
© 2013 SAP AG. All rights reserved. 11
Now we will filter out all employees who
did not have a performance rating after
th...
© 2013 SAP AG. All rights reserved. 12
© 2013 SAP AG. All rights reserved. 13
We repeat the previous steps to also
exclude employees who did not have a
performan...
© 2013 SAP AG. All rights reserved. 14
The two filters we
have just applied
Our source data has
some geographical
informat...
© 2013 SAP AG. All rights reserved. 15
© 2013 SAP AG. All rights reserved. 16
If you have additional data
like Region or City you can
create a navigation
hierarc...
© 2013 SAP AG. All rights reserved. 17
PA is quite smart and can
identify both ISO-coded
and explicitly named
geographical...
© 2013 SAP AG. All rights reserved. 18
We have finished preparation of the data
and can now proceed to visual
exploration
...
© 2013 SAP AG. All rights reserved. 19
It seems that there are
large differences in the
success ratio between
countries
© 2013 SAP AG. All rights reserved. 20
Now, let’s look at how the success
probability might be linked with moves
across jo...
© 2013 SAP AG. All rights reserved. 21
Job functions that are
quite different seem to go
along with a low
probability of s...
© 2013 SAP AG. All rights reserved. 22
The heat map tells us something about
how well certain combinations of job
function...
© 2013 SAP AG. All rights reserved. 23
The size of the rectangle
is now proportional to the
total number of moves for
this...
© 2013 SAP AG. All rights reserved. 24
Let’s switch to a different view and look at
the question: How are success probabil...
© 2013 SAP AG. All rights reserved. 25
For employees with low
performance ratings a
change of position has a
very high pro...
© 2013 SAP AG. All rights reserved. 26
We see that there are some anomalies
but so far we have only explored the data
visu...
© 2013 SAP AG. All rights reserved. 27Customer
How can we analyze the flow of people with
SAP Predictive Analysis?
1
Visua...
© 2013 SAP AG. All rights reserved. 28
Here you can see the
available algorithms that
can be applied to your
data.
In this...
© 2013 SAP AG. All rights reserved. 29
First we want to apply
some filters to the data
© 2013 SAP AG. All rights reserved. 30
© 2013 SAP AG. All rights reserved. 31
Let’s filter out the
employees without
performance ratings
© 2013 SAP AG. All rights reserved. 32
We rename the filter so
we can keep track once
the model becomes
more complex
© 2013 SAP AG. All rights reserved. 33
We configure the second filter to filter out
all dimensions that we are not going t...
© 2013 SAP AG. All rights reserved. 34
© 2013 SAP AG. All rights reserved. 35
Here we will have only
the employees and only
the dimensions we are
interested in
N...
© 2013 SAP AG. All rights reserved. 36
We’ve added the algorithm
twice to calculate two
different models on the same
data ...
© 2013 SAP AG. All rights reserved. 37
© 2013 SAP AG. All rights reserved. 38
We will use all the available
information to see what kind
of clusters the algorith...
© 2013 SAP AG. All rights reserved. 39
© 2013 SAP AG. All rights reserved. 40
…while our second analysis
will try to find ten clusters.
© 2013 SAP AG. All rights reserved. 41
Let’s run the analysis!
© 2013 SAP AG. All rights reserved. 42
© 2013 SAP AG. All rights reserved. 43
Here we can see to
which cluster a record
was assigned by the
model…
The different
...
© 2013 SAP AG. All rights reserved. 44
Here we see the
number of records that
were assigned to each
cluster in the 5-K
ana...
© 2013 SAP AG. All rights reserved. 45
Example: In cluster 1 the
average time in position
before the move was 1.53
years
W...
© 2013 SAP AG. All rights reserved. 46
Is the model with ten clusters
better than the one with five?
Let’s check…
© 2013 SAP AG. All rights reserved. 47
Two of the ten clusters are
quite heterogenous – but not
as bad as in the previous
...
© 2013 SAP AG. All rights reserved. 48
So we would prefer to use ten clusters.
But what describes these clusters?
Ordinari...
© 2013 SAP AG. All rights reserved. 49Customer
How can we analyze the flow of people with
SAP Predictive Analysis?
1
Visua...
© 2013 SAP AG. All rights reserved. 50
To answer the question:
“When is a move going to be
successful?” we will use a
deci...
© 2013 SAP AG. All rights reserved. 51
We connect the decision tree
to the first filter since we
want to use additional
co...
© 2013 SAP AG. All rights reserved. 52
From our visual exploration
we have formed the
hypothesis that the following
parame...
© 2013 SAP AG. All rights reserved. 53
We will save the decision
tree as a custom model so
we can apply it to a different
...
© 2013 SAP AG. All rights reserved. 54
Run the analysis!
© 2013 SAP AG. All rights reserved. 55
© 2013 SAP AG. All rights reserved. 56
Here we can see whether
our models thinks that a
certain move will be
successful
Bu...
© 2013 SAP AG. All rights reserved. 57
“Yes” = Position
Change will be
successful Green = relative
share with
successful m...
© 2013 SAP AG. All rights reserved. 58
Result 2: For very good ratings
the move has a much higher
chance of being successf...
© 2013 SAP AG. All rights reserved. 59
Result 3: Promotions for good
employees rarely go well when
they go along with a ch...
© 2013 SAP AG. All rights reserved. 60
This chart compares the
relative frequency of actually
successful moves against the...
© 2013 SAP AG. All rights reserved. 61
We have now created a prediction model
for success of a position change based on
hi...
© 2013 SAP AG. All rights reserved. 62Customer
How can we analyze the flow of people with
SAP Predictive Analysis?
1
Visua...
© 2013 SAP AG. All rights reserved. 63
We add a new dataset into our
analysis that contains data on
the upcoming position ...
© 2013 SAP AG. All rights reserved. 64
© 2013 SAP AG. All rights reserved. 65
© 2013 SAP AG. All rights reserved. 66
In the new dataset we have all
information that we need to
apply our decision tree
© 2013 SAP AG. All rights reserved. 67
© 2013 SAP AG. All rights reserved. 68
© 2013 SAP AG. All rights reserved. 69
© 2013 SAP AG. All rights reserved. 70
© 2013 SAP AG. All rights reserved. 71
© 2013 SAP AG. All rights reserved. 72
Here we have the predicted
results after applying our model
along with the predicte...
© 2013 SAP AG. All rights reserved. 73
Here we can use visualizations
to compare the different
success probabilities for o...
© 2013 SAP AG. All rights reserved. 74
Select what you would like to
share – e. g. your datasets,
results, visualizations,...
Henner Schliebs
Analytics Product Marketing
@hschliebs
henner
henner.schliebs@sap.com
hschliebs
Flow of people blog: http:...
Upcoming SlideShare
Loading in …5
×

Proactive Career Path Management (Talent Management)

1,374 views

Published on

Watch it in presentation mode. This demo shows the use of Predictive Analysis in a talent management context - an analysis of career movements within a given company including clustering, decision trees and more. Figure out if your talent is moving in the right direction and give advice if not to optimize your role management and investment in your workforce.
Here's a click through demo: http://bit.ly/TA-demo
Here's a 30-day trial version of the solution: http://bit.ly/try-PA

Published in: Business, Technology
  • Be the first to comment

Proactive Career Path Management (Talent Management)

  1. 1. Proactive Career Path Analysis SAP Predictive Analysis for HR Henner Schliebs, August 2013
  2. 2. © 2013 SAP AG. All rights reserved. 2Customer How can we analyze the flow of people with SAP Predictive Analysis? 1 Visually explore HR data on employee moves through the company Apply statistical algorithm to identify groups of employees with similar patterns for changing positions Derive a model that can predict the success of a change of position based on employee attributes Use this model to predict the probability of success for some upcoming moves 2 3 4
  3. 3. © 2013 SAP AG. All rights reserved. 3 Our Source data is based on Excel but could also come via HANA or BO Universe
  4. 4. © 2013 SAP AG. All rights reserved. 4
  5. 5. © 2013 SAP AG. All rights reserved. 5
  6. 6. © 2013 SAP AG. All rights reserved. 6 Here we can preview the data that is to be imported
  7. 7. © 2013 SAP AG. All rights reserved. 7 The imported data contains information on position changes as well as master data before and after the move List of dimensions inside the dataset Since Excel does not distinguish between dimensions and measures, we need to manually define our key figures for the analysis
  8. 8. © 2013 SAP AG. All rights reserved. 8 Our newly created measures Aggregation behavior
  9. 9. © 2013 SAP AG. All rights reserved. 9 Switch aggregation to “average” to calculate average success ratio of a position change
  10. 10. © 2013 SAP AG. All rights reserved. 10 Let’s rename the measures
  11. 11. © 2013 SAP AG. All rights reserved. 11 Now we will filter out all employees who did not have a performance rating after their change of position
  12. 12. © 2013 SAP AG. All rights reserved. 12
  13. 13. © 2013 SAP AG. All rights reserved. 13 We repeat the previous steps to also exclude employees who did not have a performance rating before their move (This is skipped here)
  14. 14. © 2013 SAP AG. All rights reserved. 14 The two filters we have just applied Our source data has some geographical information that can be leveraged for analysis
  15. 15. © 2013 SAP AG. All rights reserved. 15
  16. 16. © 2013 SAP AG. All rights reserved. 16 If you have additional data like Region or City you can create a navigation hierarchy that can be browsed visually
  17. 17. © 2013 SAP AG. All rights reserved. 17 PA is quite smart and can identify both ISO-coded and explicitly named geographical data
  18. 18. © 2013 SAP AG. All rights reserved. 18 We have finished preparation of the data and can now proceed to visual exploration We will start with an analysis of the success ratio of position changes along the country hierarchy we just created
  19. 19. © 2013 SAP AG. All rights reserved. 19 It seems that there are large differences in the success ratio between countries
  20. 20. © 2013 SAP AG. All rights reserved. 20 Now, let’s look at how the success probability might be linked with moves across job functions For this analysis, we will use a Heatmap with the job functions before and after as axes
  21. 21. © 2013 SAP AG. All rights reserved. 21 Job functions that are quite different seem to go along with a low probability of success… …while moves inside a job function work quite well.
  22. 22. © 2013 SAP AG. All rights reserved. 22 The heat map tells us something about how well certain combinations of job functions work together, but… …it does not take into account how frequent certain combinations appear in the first place. To analyze this we will look at a Treemap which is basically a Heatmap with a weighting factor.
  23. 23. © 2013 SAP AG. All rights reserved. 23 The size of the rectangle is now proportional to the total number of moves for this combination. These combinations are quite frequent and rarely go well.
  24. 24. © 2013 SAP AG. All rights reserved. 24 Let’s switch to a different view and look at the question: How are success probability and performance rating before the move tied together?
  25. 25. © 2013 SAP AG. All rights reserved. 25 For employees with low performance ratings a change of position has a very high probability of success. Employees with high performance ratings on the other hand have it much harder to perform equally well in their new role.
  26. 26. © 2013 SAP AG. All rights reserved. 26 We see that there are some anomalies but so far we have only explored the data visually: Nothing has yet been proven. Therefore we will now apply some statistical algorithms to see which patterns emerge scientifically.
  27. 27. © 2013 SAP AG. All rights reserved. 27Customer How can we analyze the flow of people with SAP Predictive Analysis? 1 Visually explore HR data on employee moves through the company Apply statistical algorithm to identify groups of employees with similar patterns for changing positions Derive a model that can predict the success of a change of position based on employee attributes Use this model to predict the probability of success for some upcoming moves 2 3 4
  28. 28. © 2013 SAP AG. All rights reserved. 28 Here you can see the available algorithms that can be applied to your data. In this area you can combine individual analyses to form a comprehensive model for understanding relationships.
  29. 29. © 2013 SAP AG. All rights reserved. 29 First we want to apply some filters to the data
  30. 30. © 2013 SAP AG. All rights reserved. 30
  31. 31. © 2013 SAP AG. All rights reserved. 31 Let’s filter out the employees without performance ratings
  32. 32. © 2013 SAP AG. All rights reserved. 32 We rename the filter so we can keep track once the model becomes more complex
  33. 33. © 2013 SAP AG. All rights reserved. 33 We configure the second filter to filter out all dimensions that we are not going to use in our first analyses – just to be more convenient for us.
  34. 34. © 2013 SAP AG. All rights reserved. 34
  35. 35. © 2013 SAP AG. All rights reserved. 35 Here we will have only the employees and only the dimensions we are interested in Now we add a classification algorithm that will try to find clusters of position changes with similar values in the dimensions
  36. 36. © 2013 SAP AG. All rights reserved. 36 We’ve added the algorithm twice to calculate two different models on the same data and compare them
  37. 37. © 2013 SAP AG. All rights reserved. 37
  38. 38. © 2013 SAP AG. All rights reserved. 38 We will use all the available information to see what kind of clusters the algorithm can find This first analysis will try to categorize the available data into five clusters…
  39. 39. © 2013 SAP AG. All rights reserved. 39
  40. 40. © 2013 SAP AG. All rights reserved. 40 …while our second analysis will try to find ten clusters.
  41. 41. © 2013 SAP AG. All rights reserved. 41 Let’s run the analysis!
  42. 42. © 2013 SAP AG. All rights reserved. 42
  43. 43. © 2013 SAP AG. All rights reserved. 43 Here we can see to which cluster a record was assigned by the model… The different components of our model can be viewed along with their intermediate results …but we want to see a summary of the models first.
  44. 44. © 2013 SAP AG. All rights reserved. 44 Here we see the number of records that were assigned to each cluster in the 5-K analysis This chart shows how homogenous (“dense”) the clusters are and how different from one another In this chart we can look at individual dimensions and check which dimension values were how common in each cluster This chart shows a profile diagram for each cluster (the axes are the dimensions that were put into the analysis)
  45. 45. © 2013 SAP AG. All rights reserved. 45 Example: In cluster 1 the average time in position before the move was 1.53 years We can see that most employees were assigned to this cluster and that this cluster is very heterogenous – this is a strong indicator that 5 clusters are not enough to sufficiently describe our data
  46. 46. © 2013 SAP AG. All rights reserved. 46 Is the model with ten clusters better than the one with five? Let’s check…
  47. 47. © 2013 SAP AG. All rights reserved. 47 Two of the ten clusters are quite heterogenous – but not as bad as in the previous analysis. Also: They are not as big as before – that’s a big improvement.
  48. 48. © 2013 SAP AG. All rights reserved. 48 So we would prefer to use ten clusters. But what describes these clusters? Ordinarily one would use the charts on this page or a custom visualization to find out how the clusters are comprised. We are not going to pursue this here but are going to enhance our model with a second type of analysis.
  49. 49. © 2013 SAP AG. All rights reserved. 49Customer How can we analyze the flow of people with SAP Predictive Analysis? 1 Visually explore HR data on employee moves through the company Apply statistical algorithm to identify groups of employees with similar patterns for changing positions Derive a model that can predict the success of a change of position based on employee attributes Use this model to predict the probability of success for some upcoming moves 2 3 4
  50. 50. © 2013 SAP AG. All rights reserved. 50 To answer the question: “When is a move going to be successful?” we will use a decision tree.
  51. 51. © 2013 SAP AG. All rights reserved. 51 We connect the decision tree to the first filter since we want to use additional columns that were not necessary for our previous analyses.
  52. 52. © 2013 SAP AG. All rights reserved. 52 From our visual exploration we have formed the hypothesis that the following parameters affect the probability of success: Job Function before Job Function after Performance Rating before Country AfterFrom our clustering we have found that Time in Position is important. We will additionally add: Job Level before Job Level after Change of Career Path Flag Total Tenure And we are going to model whether a move will be successful
  53. 53. © 2013 SAP AG. All rights reserved. 53 We will save the decision tree as a custom model so we can apply it to a different dataset later.
  54. 54. © 2013 SAP AG. All rights reserved. 54 Run the analysis!
  55. 55. © 2013 SAP AG. All rights reserved. 55
  56. 56. © 2013 SAP AG. All rights reserved. 56 Here we can see whether our models thinks that a certain move will be successful But let’s look at the decision tree directly
  57. 57. © 2013 SAP AG. All rights reserved. 57 “Yes” = Position Change will be successful Green = relative share with successful moves Dimension on which decision for categorization is made Result 1: If low or medium performance rating, very high probability that any move will lead to improvement
  58. 58. © 2013 SAP AG. All rights reserved. 58 Result 2: For very good ratings the move has a much higher chance of being successful if employee has been in his previous position for a long time (>3.7 years)
  59. 59. © 2013 SAP AG. All rights reserved. 59 Result 3: Promotions for good employees rarely go well when they go along with a change of job function – especially if the employee was in R&D or support before Result 4: For more customer oriented Job Functions Promotions can go very well in certain countries Complex decision tree! Let’s see how well it fits the data overall.
  60. 60. © 2013 SAP AG. All rights reserved. 60 This chart compares the relative frequency of actually successful moves against the predicted success of a move We can see that the model has some trouble predicting negative success where it has an accuracy of about 55% But if the model says a move is going to be successful, chances are quite high that it will be so in reality as well
  61. 61. © 2013 SAP AG. All rights reserved. 61 We have now created a prediction model for success of a position change based on historical data. Now we will apply this model to some upcoming moves and see what the model predicts for these employees.
  62. 62. © 2013 SAP AG. All rights reserved. 62Customer How can we analyze the flow of people with SAP Predictive Analysis? 1 Visually explore HR data on employee moves through the company Apply statistical algorithm to identify groups of employees with similar patterns for changing positions Derive a model that can predict the success of a change of position based on employee attributes Use this model to predict the probability of success for some upcoming moves 2 3 4
  63. 63. © 2013 SAP AG. All rights reserved. 63 We add a new dataset into our analysis that contains data on the upcoming position changes for seven employees
  64. 64. © 2013 SAP AG. All rights reserved. 64
  65. 65. © 2013 SAP AG. All rights reserved. 65
  66. 66. © 2013 SAP AG. All rights reserved. 66 In the new dataset we have all information that we need to apply our decision tree
  67. 67. © 2013 SAP AG. All rights reserved. 67
  68. 68. © 2013 SAP AG. All rights reserved. 68
  69. 69. © 2013 SAP AG. All rights reserved. 69
  70. 70. © 2013 SAP AG. All rights reserved. 70
  71. 71. © 2013 SAP AG. All rights reserved. 71
  72. 72. © 2013 SAP AG. All rights reserved. 72 Here we have the predicted results after applying our model along with the predicted probabilities for positive and negative success Based on the prediction – Mr. Gonzales’ move will probably lead to a lower performance after the move Mrs. Adams’ move on the other hand will most probably go well!
  73. 73. © 2013 SAP AG. All rights reserved. 73 Here we can use visualizations to compare the different success probabilities for our seven employees. Last but not least, we can share our models and predictions with our colleagues – directly from the application.
  74. 74. © 2013 SAP AG. All rights reserved. 74 Select what you would like to share – e. g. your datasets, results, visualizations,… And select how you would like to share it.
  75. 75. Henner Schliebs Analytics Product Marketing @hschliebs henner henner.schliebs@sap.com hschliebs Flow of people blog: http://bit.ly/SAP-TA-blog Talent Analytics Video: http://bit.ly/TA-YT

×