DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … ·...
Transcript of DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … ·...
![Page 1: DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … · 2019-03-29 · INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING WITH KNIME Michael](https://reader035.fdocuments.us/reader035/viewer/2022081607/5ee17aedad6a402d666c5962/html5/thumbnails/1.jpg)
1
DEUTSCHE TELEKOM AGINDIVIDUAL SOLUTIONS & PRODUCTSOPTIMIZED PREDICTIVE PLANNING WITH KNIME
Michael Schaarschmidt
Christian Gräber
March 2019
![Page 2: DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … · 2019-03-29 · INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING WITH KNIME Michael](https://reader035.fdocuments.us/reader035/viewer/2022081607/5ee17aedad6a402d666c5962/html5/thumbnails/2.jpg)
optimized Predictive Planning with KNIMEFrom Business Problem to Modeling and Implementation
implementationbusiness problem
![Page 3: DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … · 2019-03-29 · INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING WITH KNIME Michael](https://reader035.fdocuments.us/reader035/viewer/2022081607/5ee17aedad6a402d666c5962/html5/thumbnails/3.jpg)
optimized Predictive Planning with KNIMEFrom Business Problem to Modeling and Implementation
implemen-tation
businessproblem
decisionelements
underlyingdata
modelling
![Page 4: DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … · 2019-03-29 · INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING WITH KNIME Michael](https://reader035.fdocuments.us/reader035/viewer/2022081607/5ee17aedad6a402d666c5962/html5/thumbnails/4.jpg)
implemen-tation
decisionelements
underlyingdata
modelling
optimized Predictive Planning with KNIMEFrom Business Problem to Modeling and Implementation
businessproblem
![Page 5: DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … · 2019-03-29 · INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING WITH KNIME Michael](https://reader035.fdocuments.us/reader035/viewer/2022081607/5ee17aedad6a402d666c5962/html5/thumbnails/5.jpg)
Business Problem
order backlog
sales funnel
unknown business
planningsection
resource costs
![Page 6: DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … · 2019-03-29 · INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING WITH KNIME Michael](https://reader035.fdocuments.us/reader035/viewer/2022081607/5ee17aedad6a402d666c5962/html5/thumbnails/6.jpg)
Business Problem
Manuell planning time is too high in relation to the budget
Consideration of the planning part with the highest resource requirements and lowest validity
highest optimization potential
planningsection
resource costs
order backlog sales funnel unknown business
![Page 7: DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … · 2019-03-29 · INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING WITH KNIME Michael](https://reader035.fdocuments.us/reader035/viewer/2022081607/5ee17aedad6a402d666c5962/html5/thumbnails/7.jpg)
decisionelements
businessproblem
optimized Predictive Planning with KNIMEFrom Business Problem to Modeling and Implementation
implemen-tation
underlyingdata
modelling
![Page 8: DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … · 2019-03-29 · INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING WITH KNIME Michael](https://reader035.fdocuments.us/reader035/viewer/2022081607/5ee17aedad6a402d666c5962/html5/thumbnails/8.jpg)
Decision Elements
Probability of orders
Cluster & Similarities
Regression Modell
![Page 9: DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … · 2019-03-29 · INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING WITH KNIME Michael](https://reader035.fdocuments.us/reader035/viewer/2022081607/5ee17aedad6a402d666c5962/html5/thumbnails/9.jpg)
underlyingdata
decisionelements
businessproblem
optimized Predictive Planning with KNIMEFrom Business Problem to Modeling and Implementation
implemen-tation
modelling
![Page 10: DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … · 2019-03-29 · INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING WITH KNIME Michael](https://reader035.fdocuments.us/reader035/viewer/2022081607/5ee17aedad6a402d666c5962/html5/thumbnails/10.jpg)
Examples of underlying data
Customer Dimension
Sales Region
Letter of IntentTrue/False
Financial Information
project volume
term of contract
Technology & Portfolio
technology portfolio
ITIL Type
System Information
Duration per Stage
Number of offerversions
Time Dimension
Quarter of the planned project start
Condition per Stage
![Page 11: DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … · 2019-03-29 · INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING WITH KNIME Michael](https://reader035.fdocuments.us/reader035/viewer/2022081607/5ee17aedad6a402d666c5962/html5/thumbnails/11.jpg)
modellingunderlyingdata
decisionelements
businessproblem
optimized Predictive Planning with KNIMEFrom Business Problem to Modeling and Implementation
implemen-tation
![Page 12: DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … · 2019-03-29 · INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING WITH KNIME Michael](https://reader035.fdocuments.us/reader035/viewer/2022081607/5ee17aedad6a402d666c5962/html5/thumbnails/12.jpg)
Evolution of the model from simple to complex
Random Forest Learner Python & Keras Network Learner1 2
![Page 13: DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … · 2019-03-29 · INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING WITH KNIME Michael](https://reader035.fdocuments.us/reader035/viewer/2022081607/5ee17aedad6a402d666c5962/html5/thumbnails/13.jpg)
Evolution of the model from simple to complex
Random Forest Learner Python & Keras Network Learner
Retrain optimizes the existing model
Can recognize even complex relationships
Stable result even after retrain
High resource requirements for training
Special data preparation required
Scaling to range from -1 to 1 required
Requires sufficient data for initial training(approx. 1,000 data rows per feature)
Easy to implement
Can handle categorical values
No special data preparation required
Successful training even with smaller data sets
Retrain creates a new model each time
Small changes in the training data set can have a big impact on the model.
1 2
![Page 14: DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … · 2019-03-29 · INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING WITH KNIME Michael](https://reader035.fdocuments.us/reader035/viewer/2022081607/5ee17aedad6a402d666c5962/html5/thumbnails/14.jpg)
implemen-tation
modellingunderlying
datadecisionelements
businessproblem
optimized Predictive Planning with KNIMEFrom Business Problem to Modeling and Implementation
![Page 15: DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … · 2019-03-29 · INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING WITH KNIME Michael](https://reader035.fdocuments.us/reader035/viewer/2022081607/5ee17aedad6a402d666c5962/html5/thumbnails/15.jpg)
platform architecture
Temporary
raw data
Historical
data
Metadata
Dimensional
data…
![Page 16: DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … · 2019-03-29 · INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING WITH KNIME Michael](https://reader035.fdocuments.us/reader035/viewer/2022081607/5ee17aedad6a402d666c5962/html5/thumbnails/16.jpg)
integration into data warehouse
raw data
store
historical
store
KNIME
server
ETL
ETL
ETL
ETL
metadata store
execution times of individual Extract Load Transform (ETL) processes are defined in metadata management
each transaction is traceable system-wide
workflows of the individual processes read metadata, metadata controls workflows of individual processes
![Page 17: DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … · 2019-03-29 · INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING WITH KNIME Michael](https://reader035.fdocuments.us/reader035/viewer/2022081607/5ee17aedad6a402d666c5962/html5/thumbnails/17.jpg)
Keras
Implemented with Tensorflow backend
Tensorflow
Underlying framework
Currently as CPU version, GPU planned 2nd half of 2019
Python & Anaconda
Installation of Python & custom Anaconda environment
Defining the Uniform Configuration for the KNIME Server Executor
Additional Frameworks supporting Deep Learning
KNIME Server
![Page 18: DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … · 2019-03-29 · INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING WITH KNIME Michael](https://reader035.fdocuments.us/reader035/viewer/2022081607/5ee17aedad6a402d666c5962/html5/thumbnails/18.jpg)
08/17 10/1804/1802/18 08/1806/1812/1710/17
80%
06/17
60%
12/18
100%
02/190%
20%
40%
Initial situation
Long-term goal
→ Increase of accuracy of forecast and decrease of resources needed
optimized Predictive Planning with KNIME
KNIME modelfactory
neural network
testing phase AI approach
Forecast
Resources
![Page 19: DEUTSCHE TELEKOM AG INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING … · 2019-03-29 · INDIVIDUAL SOLUTIONS & PRODUCTS OPTIMIZED PREDICTIVE PLANNING WITH KNIME Michael](https://reader035.fdocuments.us/reader035/viewer/2022081607/5ee17aedad6a402d666c5962/html5/thumbnails/19.jpg)
Thank you for your attention.