Learning
from data
in A.I.M.

Learning is the act of acquiring new, or modifying and reinforcing existing, knowledge, behaviors, skills, values, or preferences which may lead to a potential change in synthesizing information, depth of the knowledge, attitude or behavior relative to the type and range of experience.

Data-driven (automated)
decisions

DATA

NEW DATA

features, summaries

features, summaries

DATA

ACTIONABLE INSIGHT

insight

  • optimal send time for Bob

  • Claire's buying probability

  • domain alerting

  • who to re-engage

Observe

Experiment

  • select relevant input data

  • train + test model on past data

  • use model on existing and new contacts

  • ...

  • (re-train model)

  • (deploy new model)

Buying prob.

Send Time Opt.

  1. any sense?

  2. best guess

  3. explore & exploit

STO w/o experiment?

train once vs cont. learning

  1. best guess

  2. explore & exploit

Incentive Reco.

Machine Learning
vs.
Learning algo

the concept of learning in data science

By Czeller Ildi

the concept of learning in data science

Slides for Emarsys AIM clan knowledge sharing talk about the concept of learning in Data Science.

  • 443