How Klarna Optimized and Personalized the Checkout Experience
Offered By: GOTO Conferences via YouTube
Course Description
Overview
Explore how Klarna optimized and personalized the checkout experience in this 28-minute conference talk from GOTO Stockholm Night 2017. Learn about Klarna's growing user base, evolving payment methods, and the challenges of offering multiple payment options. Discover how data science and machine learning techniques were applied to improve the checkout process, moving beyond simple popularity-based sorting. Gain insights into the use of classification, regression, and Random Forest models to predict user preferences. Understand the importance of features and data in creating a data-driven machine learning approach to enhance the customer experience. Follow along as Samare Jarf, a Data Scientist at Klarna, breaks down the process from problem identification to model implementation, concluding with a Q&A session.
Syllabus
Intro
Who am I
Overview
What is Checkout
OneClick vs Part Payment
Why OneClick
Hit Rate
What is Machine Learning
Determining the problem
Classification vs Regression
Features
Data
Shoe size
Model
Random Forest
Prediction
Random Forest Model
Data Driven Machine Learning
QA Session
Taught by
GOTO Conferences
Related Courses
AI for Medical PrognosisDeepLearning.AI via Coursera Predict Housing Prices in R on Boston Housing Data
Coursera Project Network via Coursera Predict Gas Guzzlers using MPG Data Set and a Random Forest
Coursera Project Network via Coursera Predict Ideal Diamonds over Good Diamonds using a Random Forest using R
Coursera Project Network via Coursera Machine Learning: Predict Poisonous Mushrooms using a Random Forest Model and the FFTrees Package in R
Coursera Project Network via Coursera