Published Apr 24, 2019

End-to-End Data Science to Drive Business Decisions at LinkedIn with Burcu Baran - TWiML Talk #256

Explore how LinkedIn's data science team, led by Burcu Baran, drives impactful business decisions through strategic model management, balancing interpretability and performance, and overcoming data handling challenges with a collaborative approach.

Episode Highlights

Topics covered

Episode Highlights

Related Episodes

Transformers for Tabular Data at Capital One with Bayan Bruss - #591
Answers 383 questions
Scaling Machine Learning on Graphs at LinkedIn with Hema Raghavan and Scott Meyer - TWiML Talk #236
Answers 383 questions
Productive Machine Learning at LinkedIn with Bee-Chung Chen - TWiML Talk #200
Answers 383 questions
Organizing for Successful Data Science at Stitch Fix with Eric Colson - TWiML Talk #257
Answers 383 questions
Applied Machine Learning for Publishers with Naveed Ahmad - TWiML Talk #182
Answers 383 questions
Jennifer Prendki Interview - Agile Machine Learning - TWiML Talk #46
Answers 383 questions
Data Pipelines at Zymergen with Airflow, w/ Erin Shellman - #41
Answers 383 questions
Live from TWIMLcon! Culture & Organization for Effective ML at Scale (Panel) - #308
Answers 383 questions
Supporting Rapid Model Development at Two Sigma with Matt Adereth & Scott Clark - TWIML Talk #273
Answers 383 questions
Productizing ML at Scale at Twitter with Yi Zhaung - TWIML Talk #271
Answers 383 questions
Privacy-Preserving Decentralized Data Science with Andrew Trask - TWiML Talk #241
Answers 383 questions
Managing Deep Learning Experiments with Lukas Biewald - TWIML Talk 295
Answers 383 questions
Live from TWIMLcon! Operationalizing ML at Scale with Hussein Mehanna - #306
Answers 383 questions
Scaling Jupyter Notebooks with Luciano Resende - TWiML Talk #261
Answers 383 questions
Scaling Enterprise ML in 2020: Still Hard! with Sushil Thomas - #429
Answers 383 questions

Dexa/This Week in ML & AI

End-to-End Data Science to Drive Business Decisions at LinkedIn with Burcu Baran - TWiML Talk #256

Topics covered

Popular Clips

Data Science Spectrum

Transition to Data Science

Efficient ML Processes

Model Evaluation Process

Model Interpretability Challenges

Coding Challenges Unveiled

Data Partitioning Strategies

Transition to Data Science

Personalized Marketing Strategies

Interpretability vs. Performance

Model Feature Segmentation

Understanding Leakage

Model Refresh Strategies

Email Campaign Strategies

Episode Highlights

Model Management Strategies

Interpretability vs Performance

Collaborative Problem Solving

Data Handling Challenges

Related Episodes

Transformers for Tabular Data at Capital One with Bayan Bruss - #591

Scaling Machine Learning on Graphs at LinkedIn with Hema Raghavan and Scott Meyer - TWiML Talk #236

Productive Machine Learning at LinkedIn with Bee-Chung Chen - TWiML Talk #200

Organizing for Successful Data Science at Stitch Fix with Eric Colson - TWiML Talk #257

Applied Machine Learning for Publishers with Naveed Ahmad - TWiML Talk #182

Jennifer Prendki Interview - Agile Machine Learning - TWiML Talk #46

Data Pipelines at Zymergen with Airflow, w/ Erin Shellman - #41

Live from TWIMLcon! Culture & Organization for Effective ML at Scale (Panel) - #308

Supporting Rapid Model Development at Two Sigma with Matt Adereth & Scott Clark - TWIML Talk #273

Productizing ML at Scale at Twitter with Yi Zhaung - TWIML Talk #271

Privacy-Preserving Decentralized Data Science with Andrew Trask - TWiML Talk #241

Managing Deep Learning Experiments with Lukas Biewald - TWIML Talk 295

Live from TWIMLcon! Operationalizing ML at Scale with Hussein Mehanna - #306

Scaling Jupyter Notebooks with Luciano Resende - TWiML Talk #261

Scaling Enterprise ML in 2020: Still Hard! with Sushil Thomas - #429

End-to-End Data Science to Drive Business Decisions at LinkedIn with Burcu Baran - TWiML Talk #256

Topics covered

Popular Clips

Episode Highlights

Model Management Strategies

Interpretability vs PerformanceBurcu Baran from LinkedIn discusses the challenges of model interpretability and the trade-offs between interpretability and performance in data science. She highlights the importance of domain knowledge and collaborative problem-solving in creating effective models.

Interpretability vs Performance

Collaborative Problem Solving

Data Handling ChallengesBurcu Baran, Senior Data Scientist at LinkedIn, discusses the comprehensive data science strategies employed to drive business decisions. She covers key aspects such as data partitioning, time alignment, and maintaining data quality to ensure accurate and effective modeling.

Data Handling Challenges

Related Episodes