~/talk

Predictive Analytics using R with Drupal

Talkat DrupalCamp Twin Cities 2018 · 2018-06-07..06-10· [drupal, machine-learning]
links:none on file
slides:none on file

Built pipeline uses Google Analytics client IDs merged with CRM records, R (caret/paradox), plumber as an API and Docker/DigitalOcean to host the model, with Drupal front-end calling the API and JavaScript swapping the homepage banner. Models train offline (70/30 split), hit about 60–64% accuracy in this deployment, use a 0.36–0.38 confidence threshold to flip content, and require nightly GA pulls. Early results show flipped-banner clicks convert ~4× better; model files are saved and served as a REST endpoint.

AI-written summary · about

  1. 0:00Start
  2. 3:17Boxed Solutions
  3. 4:46The Tools
  4. 6:14Google Analytics
  5. 9:27Tracking Users and Goal Completions
  6. 11:24Post-Data Collection
  7. 15:23Example
  8. 16:37Building a Model in R
  9. 24:51What is left
~/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.