January 19, 2023
Last Updated:
January 27, 2023

50 engineering blogs from top ML teams

Community
ML IN PRODUCTION NEWSLETTER
Best MLOps content, blogs, and events.
Thank you! Please check your email to confirm subscription!
Oops! Something went wrong while submitting the form.

Want to know how companies with top engineering teams do machine learning? We put together a list of the best company blogs that share specific ML use cases, lessons learned from building ML platforms, and insights into the tech they use. 

These are not only tech giants but companies across various industries that run engineering and tech blogs. We went through dozens of them and selected those that write about applied machine learning at least a few times a year. These blogs also cover many adjacent topics that may be interesting to data scientists and ML engineers: from data engineering to statistical experimentation platforms. Get ready for a lot of reading!

Disclaimer: information about listed blogs comes from their websites. We put it together.

Tech companies

Engineering blogs of tech companies

[fs-toc-omit]Microsoft

This multinational technology corporation has a whole blog dedicated to data science at Microsoft. The company shares lessons learned in MLOps, running machine learning models at scale, technical debt in ML, monitoring data quality, information retrieval, time series forecasting, and more.

Blogs to spotlight: 
- Python open-source libraries for scaling time series forecasting solutions
- Measuring impact in data science: Part 1

[fs-toc-omit]Google

This IT giant has not one but two blogs. Google technology blog with a dedicated AI section includes stories and updates on the cutting-edge work Google is doing in artificial intelligence and machine learning. And Google AI blog covers the latest from Google Research. 

Blogs to spotlight: 
- Model ensembles are faster than you think

- Introducing StylEx: a new approach for visual explanation of classifiers

[fs-toc-omit]NVIDIA

This technology giant takes its tech blog seriously. Under the "data science" tag, you will find dozens of machine learning use cases on scaling recommendation systems, explaining MLOps, building retail analytics applications, designing optimal AI inference pipelines for autonomous driving, and explainable AI.

Blogs to spotlight: 
- What is MLOps?

- Deep learning vs. ML challenger models for default risk with explainability

[fs-toc-omit]Amazon Science

Amazon shares the latest research from its scientists in its Amazon Science blog. The blog covers over 100 articles on machine learning. Some of the topics include federated learning, updated model backsliding, detecting bias in face recognition, scaling graph neural network training, and AutoML.

Blogs to spotlight: 
- New method identifies the root causes of statistical outliers

- Preventing updated NLP models from backsliding on particular tasks

[fs-toc-omit]Apple

Apple hosts a whole website dedicated to machine learning research. Research articles highlight ML advancements at Apple. The recent ones include 3D parametric representation, multi-task neural architecture, improving neural network subspaces, and making mobile applications more accessible. 

Blogs to spotlight: 
- Language identification from very short strings

- Interpretable adaptive optimization

[fs-toc-omit]Dropbox

A file hosting service, Dropbox, has a tech blog with machine learning among the featured topics. The blog covers topics like image search, text indexing from images, content suggestions, and optical character recognition (OCR). 

Blogs to spotlight: 
- How image search works at Dropbox

- Optimizing payments with machine learning 

E-commerce and retail

E-commerce tech blogs

[fs-toc-omit]Wayfair

Wayfair is an e-commerce company that sells furniture and home goods. Wayfair's tech blog includes over a hundred posts on data science and machine learning. Topics include Wayfair's data engine, model training workflow, building ML systems, product recommendations, ranking system, image quality prediction, and so much more.

Blogs to spotlight: 
- MARS: transformer networks for sequential recommendation

- Building scalable and performant marketing ML systems at Wayfair

[fs-toc-omit]Etsy

Etsy is an e-commerce company focused on handmade items and craft supplies. Etsy's engineering blog is called "Code as craft." Posts cover Etsy's ML platform, deep learning for search ranking, ML observability, and various ML use cases such as personalized recommendations. 

Blogs to spotlight: 
- Redesigning Etsy's machine learning platform

- Bringing personalized search to Etsy

[fs-toc-omit]Shopify

Teams that build and scale Shopify, an e-commerce platform, share their stories on an engineering blog. Data Science & Engineering section includes such topics as data-centric ML, Shopify's ML platform, building data pipelines and scaling ML. 

Blogs to spotlight: 
- 5 steps for building machine learning models for business

- Categorizing products at scale

[fs-toc-omit]OLX

OLX, an online marketplace, also has an engineering blog. It describes OLX's machine-learning use cases, including recommender systems and fraud detection. Other topics include sorting of search results, explainable AI, ML infrastructure, and how data science works at OLX.

Blogs to spotlight: 
- Fighting fraud with Triplet Loss

- Item2Vec: Neural Item Embeddings to enhance recommendations

[fs-toc-omit]Walmart

Walmart is a multinational retail corporation that operates a chain of hypermarkets, discount department stores, and grocery stores. Data science is a featured topic in Walmart's Global Tech blog. The company shares insights on AutoML, building an ML platform, using MLOps, solving routing problems, scaling product recommendations and anomaly detection. 

Blogs to spotlight: 
- Deep learning: product categorization and shelving

- Predicting defrost in refrigeration cases at Walmart using Fourier Transform

[fs-toc-omit]Stitchfix

Stitchfix is an online personal styling service. They apply machine learning in various fields, including recommendation systems, resource management, logistics optimization, demand modeling, inventory management, and algorithmic fashion design. The company describes many of these use cases in an algorithms blog that also covers ML model monitoring, ML pipelines, and model deployment.

Blogs to spotlight: 
- How algorithms are used in Stitchfix

- Algorithm-assisted inventory curation

[fs-toc-omit]Mercado Libre

Mercado Libre is an e-commerce marketplace in Latin America. The company's tech team shares its experiences and reflections in a blog. You will find pieces on building a machine learning platform, time series forecasting, causal inference, ETL flows, A/B testing, and ML project checklists. 

Blogs to spotlight: 
- Flight checks for any (big) ML project

- Why and when to build a Machine Learning Platform (part 2)

[fs-toc-omit]Zillow

Zillow, a real-estate marketplace company, also runs a tech blog. The ML & Research section covers such topics as improving the quality of recommendations, efficiently serving ML models, personalized search refinements, and image detection. 

Blogs to spotlight: 
- Improving recommendation quality by tapping into listing text
- Personalized search refinements to help customers find their dream home

Fintech and banking

Finance tech blogs

[fs-toc-omit]Capital One

Capital One is an American bank holding company specializing in credit cards, auto loans, banking, and savings accounts. The company runs a tech blog with ML and data as featured topics. It covers ML platforms and explainability, synthetic data and data-centric approach, recsys, and more. Capital One also shares papers that summarize the results of ML research they conduct. 

Blogs to spotlight: 
- Automated detection, diagnosis & remediation of app failure

- Improving virtual card numbers with edge machine learning

[fs-toc-omit]Monzo

Data Science, Analytics & ML team at Monzo online bank shares news and special project updates on Data @ Monzo blog. Every year the team shares their learnings about MLOps and the state of ML at Monzo. Other topics include Monzo's data stack, ML platform, infrastructure, AutoML, and experimentation. 

Blogs to spotlight: 
- Machine learning at Monzo in 2022

- An introduction to Monzo's data stack

[fs-toc-omit]Nubank

Nubank, a Brazilian neobank and the largest fintech bank in Latin America, also runs a blog on data science and machine learning. The blog covers automatic retraining, real-time machine learning, causal inference, ML model monitoring, and coding best practices for data scientists. 

Blogs to spotlight: 
- Machine learning model monitoring – 9 tips from the trenches

- Beyond prediction machines

[fs-toc-omit]Stripe

Stripe's engineering blog is rich in topics! They include building and operating ML infrastructure, data tools, reproducible research, and more. The blog also has in-depth guides like this one on ML for fraud detection.

Blogs to spotlight: 
- Similarity clustering to catch fraud rings

- A primer on machine learning for fraud detection

[fs-toc-omit]Rappi bank

Rappi Bank is a Colombian digital bank. The company hosts its blog on Medium. Topics cover reproducible data science, graph ML, alternative data, behavioral patterns in credit risk models,  and building data teams. 

Blogs to spotlight: 
- Introduction to graph ML

- Reproducibility in data science

[fs-toc-omit]PayPal

Machine learning is one of the featured topics of PayPal's tech blog. It covers explainable AI, graph ML, deep learning, self-supervised learning techniques, NLP, sentiment analysis, and more. 

Blogs to spotlight: 
- Using machine learning to improve payment authorization rate

- ML-centric software engineering at PayPal

[fs-toc-omit]Square

The Corner is Square's technical blog covering software engineering, APIs, data, open source, and more. Some interesting topics include metrics for product analytics, MLOps, and deep learning.  

Blogs to spotlight: 
- An overview of machine learning operations

- PySurvival tutorial: churn modeling

Travel

Booking platforms engineering blogs

[fs-toc-omit]Booking

Booking operates one of the largest online travel agencies and booking platforms. Booking's data science blog is filled with ML in production use cases. They cover ML pipelines, A/B testing and experimentation, recommender systems, and causal inference. 

Blogs to spotlight: 
- Machine learning in production: the Booking.com approach

- A auality model for machine learning systems

[fs-toc-omit]Airbnb

Airbnb operates an online marketplace focused on short-term homestays. Airbnb also runs a tech blog with data science and machine learning among its featured topics. The blog describes Airbnb's lessons learned about ML automation, deep learning, conversational AI, search ranking, computer vision, recsys, open source, and many more. 

Blogs to spotlight: 
- Intelligent automation platform: empowering conversational AI and beyond

- Improving deep learning for ranking stays at Airbnb

[fs-toc-omit]GetYourGuide

GetYourGuide, an online marketplace for tour guides and excursions, also runs a tech blog. The company built its ML platform leveraging open-source tools and shared some challenges and lessons learned. Other topics include infrastructure, improving search results, data pipelines, scaling a synthetic A/B testing platform, and building a high-performance engineering team. 

Blogs to spotlight: 
- The foundation of our open-source ML platform with a modern CI/CD pipeline
- How we extended our open-source ML platform to support real-time inference

[fs-toc-omit]Expedia

Expedia is an online travel shopping company. It hosts a tech blog that pays much attention to data and machine learning. The most interesting topics include ranking optimization, NLP model inferencing, behavioral testing, and real-time user analytics. 

Blogs to spotlight: 
- Personalized ranking model for lodging

- Going beyond scalar metrics: behavioral testing of NLP models

Media and streaming

Tech blogs of media companies

[fs-toc-omit]Netflix

Netflix, a subscription-based video streaming service, runs its tech blog. It covers topics like batch data pipelines at Netflix, orchestration of data and ML workflows, ML-based fraud detection, and recommender systems. 

Blogs to spotlight: 
- RecSysOps: best practices for operating a large-scale recommender system

- Machine learning for fraud detection in streaming services

[fs-toc-omit]Spotify

Spotify, one of the largest music streaming platforms, also has an engineering blog. The company shares its insights about data, machine learning, and infrastructure. Topics discussed include NLP, content personalization, experiments at scale, and open-source tools. 

Blogs to spotlight: 
- Product lessons from ML Home: Spotify’s one-stop shop for machine learning

- The rise (and lessons learned) of ML models to personalize content on Home

[fs-toc-omit]Scribd

Scribd is an e-book and audiobook subscription service. Its tech blog covers data engineering at Scribd, core infrastructure, recsys, internal tools they use, and more. Most interestingly, Scribd shares insights into the company's applied data science research.

Blogs to spotlight: 
- Categorizing user-uploaded documents

- Multi-armed bandits for the Win

[fs-toc-omit]Vimeo

Vimeo, a video hosting, sharing, and services platform, also runs an engineering blog. The topics include data quality monitoring, content ranking, recsys, and data orchestration. 

Blogs to spotlight: 
- Uncovering bias in search and recommendations

[fs-toc-omit]Disney Streaming

Disney Streaming, a video streaming platform, hosts its data science blog on Medium. They pay much attention to A/B testing and experimentation at scale, visualization of experiment results, and building a career in data science. 

Blogs to spotlight: 
- Universal holdout groups at Disney Streaming

[fs-toc-omit]New York Times

The New York Times Company is an American mass media company behind The New York Times. It runs a tech blog called NYT Open. The topics include recommender systems, data privacy, serving better ads, and more.

Blogs to spotlight: 
- Machine learning and reader input help us recommend articles

- How the New York Times uses machine learning to make its paywall smarter

Delivery and mobility

Engineering blogs of delivery and mobility services

[fs-toc-omit]Uber

Uber provides mobility, ride-hailing, food delivery, package delivery, and freight transportation services. Uber's engineering blog is where the company shares news and insights about technologies that power its business. The blog covers real-time document checks, offline inferences, ML infrastructure, predicting car arrival times with deep learning, fraud detection system, and more.

Blogs to spotlight: 
- Meet Michelangelo: Uber's machine learning platform

- Building a backtesting service to measure model performance at Uber-scale

[fs-toc-omit]Lyft

Lyft offers mobility, ride-hailing, and food delivery services in the United States and Canada. The company's engineering blog has data science among the featured topics. There you will find articles on various ML use cases, including causal forecasting, dynamic pricing, detecting traffic signals, and Lyft's experimentation platform and ML model training infrastructure. 

Blogs to spotlight: 
- Parameter exploration at Lyft

- LyftLearn: ML model training infrastructure built on Kubernetes

[fs-toc-omit]Doordash

Doordash's engineering blog is where the company shares insights about high-impact projects under the hood of the online delivery platform. It has about 60 blog posts that cover use cases of production machine learning and data science. Topics include deploying ML models to production, data quality issues, demand forecasting challenges, building experimentation platform, and ML model monitoring.

Blogs to spotlight: 
- How DoorDash quickly spins up multiple image recognition use cases

- Maintaining machine learning model accuracy through monitoring

[fs-toc-omit]Gojek

Gojek is an Indonesian multi-service platform with 20+ products in transport, logistics, food delivery, shopping, payments, and entertainment. The company shares its technological triumphs and challenges in a tech blog. It includes topics like batch processing pipelines, demand forecasting, experimentation, search performance, and building an ML platform. 

Blogs to spotlight: 
- How Gojek uses NLP to name pick-up locations at scale

- The secret sauce behind search personalisation

[fs-toc-omit]Grubhub

Grubhub, a US-based food delivery service, also runs an engineering blog. It covers topics like ML infrastructure, order volume forecasting, search query embeddings, and data pipelines.

Blogs to spotlight: 
- Forecasting Grubhub order volume at scale

- "Just what I needed": making ML scalable and accessible at Grubhub

[fs-toc-omit]Instacart

Instacart operates a grocery delivery and pick-up service in the United States and Canada. Its tech blog has a dedicated machine learning section as well. Some topics include real-time machine learning, Instacart's ML platform, deep learning models, marketplace balancing engine, demand prediction, and search embeddings.

Blogs to spotlight: 
- How we developed a marketplace balancing engine with ML and optimization

- How Instacart uses machine learning to spot lost demand in its fulfillment chain

[fs-toc-omit]Swiggy

India's largest online food ordering and delivery platform, Swiggy, also runs a tech blog. With various use cases in data science and machine learning, it covers routing optimization, identifying fraud rings, contextual bandits for ads recommendations, anomaly detection, and using deep learning for search ranking. 

Blogs to spotlight: 
- Multi-armed bandits at Swiggy: Part 1

- Using deep learning for ranking in dish search

[fs-toc-omit]Gousto

Gousto, a British meal kit retailer, takes its engineering blog seriously. With over 80 posts on engineering and data science, the blog covers feature stores, gradient boosting, deep learning and transformers, data engineering stack, data storytelling, andGousto's ML platform.

Blogs to spotlight: 
- Building recommender systems at Gousto

- Making agile work in data science

[fs-toc-omit]Picnic

Picnic is an online supermarket and food delivery service born in the Netherlands. It hosts a tech blog highlighting several data science and machine learning use cases. Topics include MLOps principles, Picnic's data platform, the data engineer's role in modern grocery, and more.

Blogs to spotlight: 
- Data science as a product

- The trade-off between efficiency and being on time: optimizing drop times using machine learning

Social platforms

Social networks tech blogs

[fs-toc-omit]Twitter

This social media giant shares information about the company's tools and technology on an engineering blog. Under the "machine learning" tag, you will find articles on graph machine learning, privacy and ML transparency, graph neural networks, geometric deep learning, recommender systems, and predictive algorithms. 

Blogs to spotlight: 
- Forecasting SQL query resource usage with machine learning

- Sharing learnings about our image cropping algorithm

[fs-toc-omit]LinkedIn

LinkedIn, the world's largest professional network, also runs an engineering blog rich in machine learning posts. The topics include LinkedIn's MLOps portal, graph neural networks, explainable AI, search performance, recommender systems, and ML model monitoring. 

Blogs to spotlight: 
- Our approach to building transparent and explainable AI systems

- Model health assurance platform at LinkedIn

[fs-toc-omit]Meta

The company behind Facebook, Instagram, and Whatsapp runs Meta AI blog to share its latest news on machine learning and artificial intelligence. The blog covers both ML applications and research. Topics include self-supervised learning for vision and text, generative AI, recommender systems, image generation, speech recognition, efficiency for large-scale ML models, and mitigating AI bias. 

Blogs to spotlight: 
- Harmful content can evolve quickly. Our new AI system adapts to tackle it

- Facebook's five pillars of Responsible AI

[fs-toc-omit]Bumble

Bumble Inc. is a parent company of online dating and social networking apps Bumble, Badoo, and Fruitz. It runs a tech blog with Data science as a featured topic. The blog covers topics like image detection and captioning, topic modelling, and content moderation at scale.

Blogs to spotlight:
- Evaluation of classification models on unbalanced production data

- Multilingual message content moderation at scale

[fs-toc-omit]Snap

Snap is the social media company behind Snapchat, Spectacles, and Bitmoji. The company writes about various machine learning topics on its engineering blog, including feature engineering for recsys, ad ranking, augmented reality, and device-distributed machine learning. 

Blogs to spotlight:
- Synthetic data for machine learning

- Speed up feature engineering for recommendation systems

[fs-toc-omit]Pinterest

Pinterest, an image-sharing platform, runs an engineering blog with loads of content on data science and machine learning. Since the platform focuses on user-generated content, the blog offers articles on managing UGC, optimizing content storage, improving recommender systems, and delivering relevant ads. 

Blogs to spotlight: 
- Advertiser recommendation systems at Pinterest

- How Pinterest powers a healthy comment ecosystem with machine learning

[fs-toc-omit]Nextdoor

Nextdoor is a hyperlocal social networking service for neighborhoods. The company's engineering blog covers a few interesting ML use cases, including retrieval of the search results and ranking, ML-powered notifications, identifying contentious content, typeahead search, understanding user queries, and more. 

Blogs to spotlight: 
- Nextdoor notifications: how we use ML to keep neighbors informed

Other

[fs-toc-omit]Slack

Slack is a messenger and collaboration hub for organizations and communities. In the company's engineering blog, you will find machine learning use cases on recommender systems, spam detection, email classification, and search.

Blogs to spotlight: 
- Blocking Slack invite spam with machine learning

- Email classification

[fs-toc-omit]Grammarly

Grammarly is a cloud-based typing assistant. It reviews spelling, grammar, punctuation, clarity, engagement, and delivery mistakes in texts. The company runs an engineering blog with many posts on NLP and machine learning. The use cases cover grammatical error correction, understanding conversational sequences, text simplification, and text revision.

Blogs to spotlight: 
- How Grammarly uses Natural Language Processing and Machine Learning to identify the main points in a message

[fs-toc-omit]Algolia

Algolia is a proprietary search engine. Its tech blog has a lot to share on image search, federated search, vector search, semantic search, search ranking, recommender systems, sales forecasting, and more.

Blogs to spotlight: 
- The anatomy of high-performance recommender systems – Part 1

- Visual shopping & discovery – how image search reimagines online shopping

[fs-toc-omit]More blogs to read?

That's it! We curated tech blogs from top ML teams to follow and learn from. Hope that helps to find the ones that fit your industry or use case. Of course, the list is not the ultimate, so jump to our Discord and let us know what blogs you read!

[fs-toc-omit]ML in Production blog
Evidently is an open-source tool for ML monitoring. It helps evaluate, test, and monitor the performance of ML models from validation to production. 

In our blog, we write about machine learning monitoring, MLOps, open-source and share tips from ML practitioners.

Browse the most popular blogs ⟶

Sign up for the ML in Production newsletter ⟶
https://www.linkedin.com/in/dmaliugina/
Dasha Maliugina

Community Manager

You Might Also Like:

ML in production newsletter

Get a roundup with the best blogs, links and events every month. No spam.

Thank you! Please check your email to confirm subscription!
Oops! Something went wrong while submitting the form.

By signing up you agree to receive emails from us. You can opt out any time.

January 19, 2023
Last Updated:
January 27, 2023

50 engineering blogs from top ML teams

Community
Get EVIDENTLY UPDATES
New features, integrations, and code tutorials.
Thank you! Please check your email to confirm subscription!
Oops! Something went wrong while submitting the form.

Want to know how companies with top engineering teams do machine learning? We put together a list of the best company blogs that share specific ML use cases, lessons learned from building ML platforms, and insights into the tech they use. 

These are not only tech giants but companies across various industries that run engineering and tech blogs. We went through dozens of them and selected those that write about applied machine learning at least a few times a year. These blogs also cover many adjacent topics that may be interesting to data scientists and ML engineers: from data engineering to statistical experimentation platforms. Get ready for a lot of reading!

Disclaimer: information about listed blogs comes from their websites. We put it together.

Tech companies

Engineering blogs of tech companies

[fs-toc-omit]Microsoft

This multinational technology corporation has a whole blog dedicated to data science at Microsoft. The company shares lessons learned in MLOps, running machine learning models at scale, technical debt in ML, monitoring data quality, information retrieval, time series forecasting, and more.

Blogs to spotlight: 
- Python open-source libraries for scaling time series forecasting solutions
- Measuring impact in data science: Part 1

[fs-toc-omit]Google

This IT giant has not one but two blogs. Google technology blog with a dedicated AI section includes stories and updates on the cutting-edge work Google is doing in artificial intelligence and machine learning. And Google AI blog covers the latest from Google Research. 

Blogs to spotlight: 
- Model ensembles are faster than you think

- Introducing StylEx: a new approach for visual explanation of classifiers

[fs-toc-omit]NVIDIA

This technology giant takes its tech blog seriously. Under the "data science" tag, you will find dozens of machine learning use cases on scaling recommendation systems, explaining MLOps, building retail analytics applications, designing optimal AI inference pipelines for autonomous driving, and explainable AI.

Blogs to spotlight: 
- What is MLOps?

- Deep learning vs. ML challenger models for default risk with explainability

[fs-toc-omit]Amazon Science

Amazon shares the latest research from its scientists in its Amazon Science blog. The blog covers over 100 articles on machine learning. Some of the topics include federated learning, updated model backsliding, detecting bias in face recognition, scaling graph neural network training, and AutoML.

Blogs to spotlight: 
- New method identifies the root causes of statistical outliers

- Preventing updated NLP models from backsliding on particular tasks

[fs-toc-omit]Apple

Apple hosts a whole website dedicated to machine learning research. Research articles highlight ML advancements at Apple. The recent ones include 3D parametric representation, multi-task neural architecture, improving neural network subspaces, and making mobile applications more accessible. 

Blogs to spotlight: 
- Language identification from very short strings

- Interpretable adaptive optimization

[fs-toc-omit]Dropbox

A file hosting service, Dropbox, has a tech blog with machine learning among the featured topics. The blog covers topics like image search, text indexing from images, content suggestions, and optical character recognition (OCR). 

Blogs to spotlight: 
- How image search works at Dropbox

- Optimizing payments with machine learning 

E-commerce and retail

E-commerce tech blogs

[fs-toc-omit]Wayfair

Wayfair is an e-commerce company that sells furniture and home goods. Wayfair's tech blog includes over a hundred posts on data science and machine learning. Topics include Wayfair's data engine, model training workflow, building ML systems, product recommendations, ranking system, image quality prediction, and so much more.

Blogs to spotlight: 
- MARS: transformer networks for sequential recommendation

- Building scalable and performant marketing ML systems at Wayfair

[fs-toc-omit]Etsy

Etsy is an e-commerce company focused on handmade items and craft supplies. Etsy's engineering blog is called "Code as craft." Posts cover Etsy's ML platform, deep learning for search ranking, ML observability, and various ML use cases such as personalized recommendations. 

Blogs to spotlight: 
- Redesigning Etsy's machine learning platform

- Bringing personalized search to Etsy

[fs-toc-omit]Shopify

Teams that build and scale Shopify, an e-commerce platform, share their stories on an engineering blog. Data Science & Engineering section includes such topics as data-centric ML, Shopify's ML platform, building data pipelines and scaling ML. 

Blogs to spotlight: 
- 5 steps for building machine learning models for business

- Categorizing products at scale

[fs-toc-omit]OLX

OLX, an online marketplace, also has an engineering blog. It describes OLX's machine-learning use cases, including recommender systems and fraud detection. Other topics include sorting of search results, explainable AI, ML infrastructure, and how data science works at OLX.

Blogs to spotlight: 
- Fighting fraud with Triplet Loss

- Item2Vec: Neural Item Embeddings to enhance recommendations

[fs-toc-omit]Walmart

Walmart is a multinational retail corporation that operates a chain of hypermarkets, discount department stores, and grocery stores. Data science is a featured topic in Walmart's Global Tech blog. The company shares insights on AutoML, building an ML platform, using MLOps, solving routing problems, scaling product recommendations and anomaly detection. 

Blogs to spotlight: 
- Deep learning: product categorization and shelving

- Predicting defrost in refrigeration cases at Walmart using Fourier Transform

[fs-toc-omit]Stitchfix

Stitchfix is an online personal styling service. They apply machine learning in various fields, including recommendation systems, resource management, logistics optimization, demand modeling, inventory management, and algorithmic fashion design. The company describes many of these use cases in an algorithms blog that also covers ML model monitoring, ML pipelines, and model deployment.

Blogs to spotlight: 
- How algorithms are used in Stitchfix

- Algorithm-assisted inventory curation

[fs-toc-omit]Mercado Libre

Mercado Libre is an e-commerce marketplace in Latin America. The company's tech team shares its experiences and reflections in a blog. You will find pieces on building a machine learning platform, time series forecasting, causal inference, ETL flows, A/B testing, and ML project checklists. 

Blogs to spotlight: 
- Flight checks for any (big) ML project

- Why and when to build a Machine Learning Platform (part 2)

[fs-toc-omit]Zillow

Zillow, a real-estate marketplace company, also runs a tech blog. The ML & Research section covers such topics as improving the quality of recommendations, efficiently serving ML models, personalized search refinements, and image detection. 

Blogs to spotlight: 
- Improving recommendation quality by tapping into listing text
- Personalized search refinements to help customers find their dream home

Fintech and banking

Finance tech blogs

[fs-toc-omit]Capital One

Capital One is an American bank holding company specializing in credit cards, auto loans, banking, and savings accounts. The company runs a tech blog with ML and data as featured topics. It covers ML platforms and explainability, synthetic data and data-centric approach, recsys, and more. Capital One also shares papers that summarize the results of ML research they conduct. 

Blogs to spotlight: 
- Automated detection, diagnosis & remediation of app failure

- Improving virtual card numbers with edge machine learning

[fs-toc-omit]Monzo

Data Science, Analytics & ML team at Monzo online bank shares news and special project updates on Data @ Monzo blog. Every year the team shares their learnings about MLOps and the state of ML at Monzo. Other topics include Monzo's data stack, ML platform, infrastructure, AutoML, and experimentation. 

Blogs to spotlight: 
- Machine learning at Monzo in 2022

- An introduction to Monzo's data stack

[fs-toc-omit]Nubank

Nubank, a Brazilian neobank and the largest fintech bank in Latin America, also runs a blog on data science and machine learning. The blog covers automatic retraining, real-time machine learning, causal inference, ML model monitoring, and coding best practices for data scientists. 

Blogs to spotlight: 
- Machine learning model monitoring – 9 tips from the trenches

- Beyond prediction machines

[fs-toc-omit]Stripe

Stripe's engineering blog is rich in topics! They include building and operating ML infrastructure, data tools, reproducible research, and more. The blog also has in-depth guides like this one on ML for fraud detection.

Blogs to spotlight: 
- Similarity clustering to catch fraud rings

- A primer on machine learning for fraud detection

[fs-toc-omit]Rappi bank

Rappi Bank is a Colombian digital bank. The company hosts its blog on Medium. Topics cover reproducible data science, graph ML, alternative data, behavioral patterns in credit risk models,  and building data teams. 

Blogs to spotlight: 
- Introduction to graph ML

- Reproducibility in data science

[fs-toc-omit]PayPal

Machine learning is one of the featured topics of PayPal's tech blog. It covers explainable AI, graph ML, deep learning, self-supervised learning techniques, NLP, sentiment analysis, and more. 

Blogs to spotlight: 
- Using machine learning to improve payment authorization rate

- ML-centric software engineering at PayPal

[fs-toc-omit]Square

The Corner is Square's technical blog covering software engineering, APIs, data, open source, and more. Some interesting topics include metrics for product analytics, MLOps, and deep learning.  

Blogs to spotlight: 
- An overview of machine learning operations

- PySurvival tutorial: churn modeling

Travel

Booking platforms engineering blogs

[fs-toc-omit]Booking

Booking operates one of the largest online travel agencies and booking platforms. Booking's data science blog is filled with ML in production use cases. They cover ML pipelines, A/B testing and experimentation, recommender systems, and causal inference. 

Blogs to spotlight: 
- Machine learning in production: the Booking.com approach

- A auality model for machine learning systems

[fs-toc-omit]Airbnb

Airbnb operates an online marketplace focused on short-term homestays. Airbnb also runs a tech blog with data science and machine learning among its featured topics. The blog describes Airbnb's lessons learned about ML automation, deep learning, conversational AI, search ranking, computer vision, recsys, open source, and many more. 

Blogs to spotlight: 
- Intelligent automation platform: empowering conversational AI and beyond

- Improving deep learning for ranking stays at Airbnb

[fs-toc-omit]GetYourGuide

GetYourGuide, an online marketplace for tour guides and excursions, also runs a tech blog. The company built its ML platform leveraging open-source tools and shared some challenges and lessons learned. Other topics include infrastructure, improving search results, data pipelines, scaling a synthetic A/B testing platform, and building a high-performance engineering team. 

Blogs to spotlight: 
- The foundation of our open-source ML platform with a modern CI/CD pipeline
- How we extended our open-source ML platform to support real-time inference

[fs-toc-omit]Expedia

Expedia is an online travel shopping company. It hosts a tech blog that pays much attention to data and machine learning. The most interesting topics include ranking optimization, NLP model inferencing, behavioral testing, and real-time user analytics. 

Blogs to spotlight: 
- Personalized ranking model for lodging

- Going beyond scalar metrics: behavioral testing of NLP models

Media and streaming

Tech blogs of media companies

[fs-toc-omit]Netflix

Netflix, a subscription-based video streaming service, runs its tech blog. It covers topics like batch data pipelines at Netflix, orchestration of data and ML workflows, ML-based fraud detection, and recommender systems. 

Blogs to spotlight: 
- RecSysOps: best practices for operating a large-scale recommender system

- Machine learning for fraud detection in streaming services

[fs-toc-omit]Spotify

Spotify, one of the largest music streaming platforms, also has an engineering blog. The company shares its insights about data, machine learning, and infrastructure. Topics discussed include NLP, content personalization, experiments at scale, and open-source tools. 

Blogs to spotlight: 
- Product lessons from ML Home: Spotify’s one-stop shop for machine learning

- The rise (and lessons learned) of ML models to personalize content on Home

[fs-toc-omit]Scribd

Scribd is an e-book and audiobook subscription service. Its tech blog covers data engineering at Scribd, core infrastructure, recsys, internal tools they use, and more. Most interestingly, Scribd shares insights into the company's applied data science research.

Blogs to spotlight: 
- Categorizing user-uploaded documents

- Multi-armed bandits for the Win

[fs-toc-omit]Vimeo

Vimeo, a video hosting, sharing, and services platform, also runs an engineering blog. The topics include data quality monitoring, content ranking, recsys, and data orchestration. 

Blogs to spotlight: 
- Uncovering bias in search and recommendations

[fs-toc-omit]Disney Streaming

Disney Streaming, a video streaming platform, hosts its data science blog on Medium. They pay much attention to A/B testing and experimentation at scale, visualization of experiment results, and building a career in data science. 

Blogs to spotlight: 
- Universal holdout groups at Disney Streaming

[fs-toc-omit]New York Times

The New York Times Company is an American mass media company behind The New York Times. It runs a tech blog called NYT Open. The topics include recommender systems, data privacy, serving better ads, and more.

Blogs to spotlight: 
- Machine learning and reader input help us recommend articles

- How the New York Times uses machine learning to make its paywall smarter

Delivery and mobility

Engineering blogs of delivery and mobility services

[fs-toc-omit]Uber

Uber provides mobility, ride-hailing, food delivery, package delivery, and freight transportation services. Uber's engineering blog is where the company shares news and insights about technologies that power its business. The blog covers real-time document checks, offline inferences, ML infrastructure, predicting car arrival times with deep learning, fraud detection system, and more.

Blogs to spotlight: 
- Meet Michelangelo: Uber's machine learning platform

- Building a backtesting service to measure model performance at Uber-scale

[fs-toc-omit]Lyft

Lyft offers mobility, ride-hailing, and food delivery services in the United States and Canada. The company's engineering blog has data science among the featured topics. There you will find articles on various ML use cases, including causal forecasting, dynamic pricing, detecting traffic signals, and Lyft's experimentation platform and ML model training infrastructure. 

Blogs to spotlight: 
- Parameter exploration at Lyft

- LyftLearn: ML model training infrastructure built on Kubernetes

[fs-toc-omit]Doordash

Doordash's engineering blog is where the company shares insights about high-impact projects under the hood of the online delivery platform. It has about 60 blog posts that cover use cases of production machine learning and data science. Topics include deploying ML models to production, data quality issues, demand forecasting challenges, building experimentation platform, and ML model monitoring.

Blogs to spotlight: 
- How DoorDash quickly spins up multiple image recognition use cases

- Maintaining machine learning model accuracy through monitoring

[fs-toc-omit]Gojek

Gojek is an Indonesian multi-service platform with 20+ products in transport, logistics, food delivery, shopping, payments, and entertainment. The company shares its technological triumphs and challenges in a tech blog. It includes topics like batch processing pipelines, demand forecasting, experimentation, search performance, and building an ML platform. 

Blogs to spotlight: 
- How Gojek uses NLP to name pick-up locations at scale

- The secret sauce behind search personalisation

[fs-toc-omit]Grubhub

Grubhub, a US-based food delivery service, also runs an engineering blog. It covers topics like ML infrastructure, order volume forecasting, search query embeddings, and data pipelines.

Blogs to spotlight: 
- Forecasting Grubhub order volume at scale

- "Just what I needed": making ML scalable and accessible at Grubhub

[fs-toc-omit]Instacart

Instacart operates a grocery delivery and pick-up service in the United States and Canada. Its tech blog has a dedicated machine learning section as well. Some topics include real-time machine learning, Instacart's ML platform, deep learning models, marketplace balancing engine, demand prediction, and search embeddings.

Blogs to spotlight: 
- How we developed a marketplace balancing engine with ML and optimization

- How Instacart uses machine learning to spot lost demand in its fulfillment chain

[fs-toc-omit]Swiggy

India's largest online food ordering and delivery platform, Swiggy, also runs a tech blog. With various use cases in data science and machine learning, it covers routing optimization, identifying fraud rings, contextual bandits for ads recommendations, anomaly detection, and using deep learning for search ranking. 

Blogs to spotlight: 
- Multi-armed bandits at Swiggy: Part 1

- Using deep learning for ranking in dish search

[fs-toc-omit]Gousto

Gousto, a British meal kit retailer, takes its engineering blog seriously. With over 80 posts on engineering and data science, the blog covers feature stores, gradient boosting, deep learning and transformers, data engineering stack, data storytelling, andGousto's ML platform.

Blogs to spotlight: 
- Building recommender systems at Gousto

- Making agile work in data science

[fs-toc-omit]Picnic

Picnic is an online supermarket and food delivery service born in the Netherlands. It hosts a tech blog highlighting several data science and machine learning use cases. Topics include MLOps principles, Picnic's data platform, the data engineer's role in modern grocery, and more.

Blogs to spotlight: 
- Data science as a product

- The trade-off between efficiency and being on time: optimizing drop times using machine learning

Social platforms

Social networks tech blogs

[fs-toc-omit]Twitter

This social media giant shares information about the company's tools and technology on an engineering blog. Under the "machine learning" tag, you will find articles on graph machine learning, privacy and ML transparency, graph neural networks, geometric deep learning, recommender systems, and predictive algorithms. 

Blogs to spotlight: 
- Forecasting SQL query resource usage with machine learning

- Sharing learnings about our image cropping algorithm

[fs-toc-omit]LinkedIn

LinkedIn, the world's largest professional network, also runs an engineering blog rich in machine learning posts. The topics include LinkedIn's MLOps portal, graph neural networks, explainable AI, search performance, recommender systems, and ML model monitoring. 

Blogs to spotlight: 
- Our approach to building transparent and explainable AI systems

- Model health assurance platform at LinkedIn

[fs-toc-omit]Meta

The company behind Facebook, Instagram, and Whatsapp runs Meta AI blog to share its latest news on machine learning and artificial intelligence. The blog covers both ML applications and research. Topics include self-supervised learning for vision and text, generative AI, recommender systems, image generation, speech recognition, efficiency for large-scale ML models, and mitigating AI bias. 

Blogs to spotlight: 
- Harmful content can evolve quickly. Our new AI system adapts to tackle it

- Facebook's five pillars of Responsible AI

[fs-toc-omit]Bumble

Bumble Inc. is a parent company of online dating and social networking apps Bumble, Badoo, and Fruitz. It runs a tech blog with Data science as a featured topic. The blog covers topics like image detection and captioning, topic modelling, and content moderation at scale.

Blogs to spotlight:
- Evaluation of classification models on unbalanced production data

- Multilingual message content moderation at scale

[fs-toc-omit]Snap

Snap is the social media company behind Snapchat, Spectacles, and Bitmoji. The company writes about various machine learning topics on its engineering blog, including feature engineering for recsys, ad ranking, augmented reality, and device-distributed machine learning. 

Blogs to spotlight:
- Synthetic data for machine learning

- Speed up feature engineering for recommendation systems

[fs-toc-omit]Pinterest

Pinterest, an image-sharing platform, runs an engineering blog with loads of content on data science and machine learning. Since the platform focuses on user-generated content, the blog offers articles on managing UGC, optimizing content storage, improving recommender systems, and delivering relevant ads. 

Blogs to spotlight: 
- Advertiser recommendation systems at Pinterest

- How Pinterest powers a healthy comment ecosystem with machine learning

[fs-toc-omit]Nextdoor

Nextdoor is a hyperlocal social networking service for neighborhoods. The company's engineering blog covers a few interesting ML use cases, including retrieval of the search results and ranking, ML-powered notifications, identifying contentious content, typeahead search, understanding user queries, and more. 

Blogs to spotlight: 
- Nextdoor notifications: how we use ML to keep neighbors informed

Other

[fs-toc-omit]Slack

Slack is a messenger and collaboration hub for organizations and communities. In the company's engineering blog, you will find machine learning use cases on recommender systems, spam detection, email classification, and search.

Blogs to spotlight: 
- Blocking Slack invite spam with machine learning

- Email classification

[fs-toc-omit]Grammarly

Grammarly is a cloud-based typing assistant. It reviews spelling, grammar, punctuation, clarity, engagement, and delivery mistakes in texts. The company runs an engineering blog with many posts on NLP and machine learning. The use cases cover grammatical error correction, understanding conversational sequences, text simplification, and text revision.

Blogs to spotlight: 
- How Grammarly uses Natural Language Processing and Machine Learning to identify the main points in a message

[fs-toc-omit]Algolia

Algolia is a proprietary search engine. Its tech blog has a lot to share on image search, federated search, vector search, semantic search, search ranking, recommender systems, sales forecasting, and more.

Blogs to spotlight: 
- The anatomy of high-performance recommender systems – Part 1

- Visual shopping & discovery – how image search reimagines online shopping

[fs-toc-omit]More blogs to read?

That's it! We curated tech blogs from top ML teams to follow and learn from. Hope that helps to find the ones that fit your industry or use case. Of course, the list is not the ultimate, so jump to our Discord and let us know what blogs you read!

[fs-toc-omit]ML in Production blog
Evidently is an open-source tool for ML monitoring. It helps evaluate, test, and monitor the performance of ML models from validation to production. 

In our blog, we write about machine learning monitoring, MLOps, open-source and share tips from ML practitioners.

Browse the most popular blogs ⟶

Sign up for the ML in Production newsletter ⟶
https://www.linkedin.com/in/dmaliugina/
Dasha Maliugina

Community Manager

You Might Also Like:

ML in production newsletter

Get a roundup with the best blogs, links and events every month. No spam.

Thank you! Please check your email to confirm subscription!
Oops! Something went wrong while submitting the form.

By signing up you agree to receive emails from us. You can opt out any time.

By clicking “Accept”, you agree to the storing of cookies on your device to enhance site navigation, analyze site usage, and assist in our marketing efforts. View our Privacy Policy for more information.