~/talk

Carlos Guevara, Claro Colombia & Carlo Appugliese, IBM | IBM Think 2019

Talkat IBM Think 2019 · 2019-02-12..02-15· [data-science, machine-learning]
links:none on file
links:none on file
slides:none on file

Claro Colombia and IBM Data Science Elite ingest terabytes of usage and billing data from a fragmented Hadoop estate, train XGBoost models that hit 90–92% precision, and push scores into mobile applications for real‑time targeting. The workflow uses Spark and ICP for Data to clean and govern inputs, uncovers root causes (billing and invoice issues explain large churn cohorts), and produces prescriptive actions after an initial loss of about 50,000 customers before interventions were applied.

AI-written summary · about

  1. 0:00Introduction to IBM Think 2019
  2. 0:45AI and data challenges in telecom
  3. 1:05Claro Colombia's churn problem
  4. 3:37IBM Data Science Elite Team approach
  5. 5:02From prediction to business action
  6. 6:06Data lake and model deployment
  7. 7:55Evolution of data science roles
  8. 9:20Real-time predictive models
  9. 10:02Key learnings from the project
  10. 12:30CDO's role in monetizing data
  11. 12:51IBM Data Science Elite Team explained
~/search
type to search 6,518 conferences, 143,918 speakers and 192,133 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
← →
on a talk: 5 seconds back / forward
0–9
on a talk: jump to 0%–90% of the recording
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.