Outline
- data types/concepts
- people behaviour
- tuning/predictions
Data privacy
- handover between cells - calls/internet package
- no content/size information
- new hashed id every day
- no group (age, device, zip...) below 30 people
event collection
![event collection](../f/f_comm/event_collection.svg)
We collect an handover between cells per device (D1-Netz)
Events to movements
![event collection](../f/f_comm/event_activity.svg)
We groups events into activities and trips
Activity probability
![event collection](../f/f_comm/activity_density.png)
Density probability of activities between cells
User's behaviour
![event collection](../f/f_comm/shapeCluster.svg)
Different signaling patterns during the day
Daily patterns
![event collection](../f/f_comm/daily_movements.svg)
People have different patterns every day
Tourist patterns
![event collection](../f/f_comm/tourist_origin.png)
Split nationality, origin, counting activities
age, gender, device types
![event collection](../f/f_comm/age_gender1.png)
Distribution of age classes per zip code
From cells to routes
- Interpret cell connection during a trip
- Understand mode of transportation
- Calculate most probable route
- Count people
movements across the country
![event collection](../f/f_comm/odm_trajectory.svg)
How people move during a day
Most frequent origin and destination
![event collection](../f/f_comm/odm_local.png)
important for local transportation companies
routing/infrastructure
![event collection](../f/f_comm/routing_junction.png)
we work on an efficient routing and infrastructure
local network
![event collection](../f/f_comm/local_network.svg)
Special modules consider city centers
subway module
![event collection](../f/f_comm/subway_module.svg)
Distinguish the mean of transportation labelling cells (training data)
subway passangers
![event collection](../f/f_comm/subway_time.png)
Collecting information about commuters
Use of information
- activities, footfalls, section counts
- points of interest/geo context
- statistical geographical population data
- public/training reference data
Intensity of activities
![event collection](../f/f_comm/heatmap_break.png)
Activity intensity: breaks of motorway drivers
geographical data
![event collection](../f/f_comm/data_enrichment.png)
Validate results with statistical data (population density)
collect important features
![event collection](../f/f_comm/feature_wordcloud.png)
we select the most relevant features
training set
![event collection](../f/f_comm/selected_features.png)
geographical information to train system
training
![event collection](../f/f_comm/regression_tree.png)
We train our models to predict success
compare external sources
![event collection](../f/f_comm/reference_data1.png)
Public information from different sources
forecast
![event collection](../f/f_comm/animatePer1.gif)
We use past time series for forecasting events
mapping on offer
![event collection](../f/f_comm/whitespot_restaurant.png)
Calculate the coverage of a commercial activity
whitespot analysis
![event collection](../f/f_comm/whitespot_analysis1.png)
Customer potential on regions not covered within a isochrone
Thank you
for your attention