More Related Content Similar to Internet of Things trifft auf Customer Intelligence (20) More from Rising Media Ltd. (20) Internet of Things trifft auf Customer Intelligence1. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED.
The Internet of Things
Aaron Hart
Dr. Rosaria Silipo
Phil Winters
2. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 2
Customer Strategy
Customer Perspective
Chamption
3. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 3
The Customer’s Perspective
Decision Cycle and Touchpoints
g
@
Ad
g
g
4. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 4
• Defining the Customer Perspective
• Identifying new Touchpoints
• Using new Customer Insight
• Give to Get: Information Strategies
• Social Media
• Mobile
• Big Data
• Sales Cycle Transformation
• Touchpoint Choreography
• Customer Delight
• Multi-Industry / Multi- Product processes optimization
Selected Topics
Doing Business from the Customer’s Perspective
5. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 5
Where you can find more:
Customer IMPACT Agenda
The Speeches
The Book
The Workshop
www.ciagenda.com
phil.winters@ciagenda.com
auch auf Deutsch!
6. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 6
Customer Strategy
Data Whisperer Customer Perspective
Chamption
7. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 7
Customer Intelligence – creating new fact-base insight from data
Data Whisperer
Needs
Behavior
Value
drivesgenerates
Dimension Needs Dimension Behavior Dimension Needs
8. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 8
PAW 2012: Text Mining meets Network Mining
8
Text Mining for Sentiment
Drill Down on special cases
Network Mining for Relevance
Analytics for Prediction
9. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 9
• Telemetry Data
• Time Series Analysis
with clustering
• Measurable / Applied to the Business
• SENSIBLE usages of Big Data
PAW 2013: Time Series meets Machine Learning
10. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 10
2014: It’s all Geert’s Fault: The Internet of Things
Illustration by CRISTINA BYVIK
Use Public Data Please….
11. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 11
Original:
12. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 12
Washington DC
13. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 13
Sensors!
15. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 15
KNIME and the Internet of Things
16. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 16
Reading Sensor data is always messy……
14 Quarters of Sensor Data….
But good packages
make it easy to do !
17. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 17
Reading the Sensor Data
18. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 18
Street Maps
Weather
Holiday Schedules
Commuters
Tourists
Topology / Elevations
Enrich
19. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 19
Enrich
The power of REST services and the Internet…………
20. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 20
Enrich
21. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 21
Enrich
22. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 22
Expand
23. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 23
Station and Bike Facts
Over 3 years
307 Stations
2963 Bikes
19.4% Casual Bikers
5.9m Bike Moves
24. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 24
The 30 minute rule…
Under 30 30 and Over
Casual 63% 37%
Subscriber 98% 2%
Overall 91% 9%
25. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 25
Most Popular Segment:
Jefferson Memorial to the Lincoln Memorial
89% Casual Users!
26. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 26
The Business Challenge:
27. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 27
Even MORE of a Business Challenge
Any Station without bikes for 1 hour:
$XXXX Per Violation
Any Station with no free slots for 1 hour:
$XXXX Per Violation
28. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 28
The Business Challenge: 12th and Bell St.
-587 Bikes
29. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 29
The Business Challenge: 12th Street and Bell
30. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 30
“Helpful” Bike Enthusiasts
http://www.cabitracker.com/status.php
31. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 31
http://bikeportland.org/2013/03/10/behind-the-scenes-of-capital-bikeshare-84006
Capital Bikeshare Response
32. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 32
Station Totals per hour
33. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 33
Creating the Video…..
• Open Street Map (OSM)
• Image Processing
• Group Loop
34. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 34
Station Totals per hour (the video)
35. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 35
Lean Restocking Alert System
• Goal: Implement an alert signal for when shifting stock (both
adding and removing bikes) may be needed in a station.
• Target Variable:
Flag and Shifted contain the current human operated
restocking information.
• We want 1 hour warning!
Lag(flag-1)
36. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 36
29 Input Features!
- Weather related features
- Number of registered and casual people showing up
- Station info (name and max. number of docks)
- Calendar info (working day, holiday, date)
- Count as the number of bikes added and removed at
each hour
- Past bike ratios over time at that station
• Adjusted cumulative sum as the number of bikes available at
the station at a given hour
• Bike ratio = adjusted cumulative sum/total docks available.
Predict an Alert 1 hour in advance of a “full” or “empty” situation
Lean Restocking Alert System
37. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 37
Linear Correlation on the Input Data Columns
38. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 38
Feature Elimination Loop
Two options:
1. Use all the input features
(no thinking required, just a powerful machine)
2. Select the most useful input features via “Feature Elimination”
At each step one
input feature is
removed- i.e. the
input feature
whose removal
produces the
smallest error
increase.
39. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 39
“Backward Feature Elimination Filter” node
40. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 40
“Lean Restocking Alert System” workflow
The input feature subset with the
smallest error (81% accuracy) is
forwarded to the final model
training block:
• Hour of the day
• working day (Y/N)
• Current Bike Ratio
• Terminal (station code)
past Bike Ratios and weather info
does not seem to be relevant!
41. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 41
Total Bikers Predicted by Hour of days
• Registered (blue) vs. Casual (red) Bikers
42. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 42
Time Series Prediction
- Define Time series lags by hand or……
- Select the best values programmatically using an Optimization
Parameter Loop!
43. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 43
Parameter Optimization Loop
Looping over different values for
lagging and seasonality index
(Brute Force or Hillclimbing).
Collecting the RMS error at the end
of the loop.
Selecting the parameter set with
minimum RMS error.
44. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 44
“Bikers Prediction” workflow
Parameter
Optimization
Loop
Time Series Prediction Metanodes
Seasonality
index
Past lags RMS Error
casual 1hour 20 13.8
registered 24 hours 10 68.3
45. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 45
Conclusions….
- Best Input Feature Subset using the
“Feature Elimination” Metanode
- Best Parameter Set for Time Series Prediction
using the “Parameter Optimization” node
- Weather influence on bikers is overrated!
- Casual Bikers 24 hours Seasonality is also not so
relevant!
46. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 46
Top Net Bike Change Stations
47. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 47
Stations with deficits and surpluses
Bike sources
Bike Sinks
16th and Harvard
Union Station
48. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 48
NetChanges
Total Traffic Volume
Bike sources
Bike Sinks
16th and Harvard
Union Station
And now some analysis…
49. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 49
Finding route data
(Just google it)
50. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 50
REST Webservices with KNIME
http://maps.googleapis.com/maps/api/directions/json?
&origin=lat,long&destination=lat,long&mode=bicycling
https://developers.google.com/maps/documentation/directions/
51. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 51
Then Plot the Routes!
Union Station
52. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 52
Finding route data
(Just google it)
53. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 53
Convert to a Network for Network Analysis
54. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 54
Urban/
Students
Suburban
Tourists
Top 250 Routes
Dupont Circle
Union Station
55. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 55
Union Station Subnet
56. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 56
Dupont Circle Subnet
58. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 58
Possible Next Steps
• Combine Prediction with Path !!!!
• Enrich through analyzing images
+
59. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 59
IOT Lessons Learned
• IOT (Sensor) Data is simple… but can still be messy
– get it in, get it clean!
• Connect it!
– Common keys, Lat/long, time, etc.
– No common key? Network analysis + Imaging
• Enrich / Expand
– Transformation
– External Sources; REST calls; Palladian, etc.
• Explore
– Visualization (over time!) OSM, Imaging
– Network Analysis
– Correlation matrix!
• Prediction
– Feature Elimination for Input Feature Set + “Classic Machine Learning Techniques”
– Parameter Optimization + “Classic Time Series Techniques”
60. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 60
It’s all Geert’s Fault: The Internet of Things
Illustration by CRISTINA BYVIK
Use Public Data Please….
61. COPYRIGHT © 2014 BY PHIL WINTERS. ALL RIGHTS PROTECTED AND RESERVED. 61
The Internet of Things:
White paper, Workflows, Data are now available
Taming the Internet of Things with KNIME:
Data Enrichment, Visualization,
Time Series Analysis, and Optimization
http://www.knime.com/white-papers#IoT