~/devreads

#data science

29 posts

2 Jun

Harrison Katz 11 min read

How Airbnb used sequential geographic recovery signals and prior propagation to generate reliable corridor-level forecasts when local data was scarce. By: Harrison Katz The problem with unprecedented shocks Almost every forecasting system is built on the same implicit assumption: the future will resemble the past. You train on historical data, you validate on holdout periods, and you trust that past…

technologymachine-learningdata-sciencedata-modelingforecasting

29 May

Yash Khandelwal 12 min read

The Problem A Delivery Executive (DE) finishes their day, opens the app, and expects a clear breakdown of what they earned. Instead, they often see a payout that does not fully match their expectations — an incentive missing, a deduction they do not recognise, or a credited amount lower than what they had mentally calculated. At Swiggy, these seemingly simple…

customer-experienceartificial-intelligencelarge-language-modelsagentic-aidata-science

18 May

5 May

Piyush Vyas 9 min read

In the world of e-commerce, a click of a “Buy Now” button starts an invisible race. Across India (metro cities or remote villages) millions of customers expect their packages to arrive with a speed that feels like magic. But behind that “magic” is a monumental logistical puzzle. At Flipkart, we serve over 500 million registered users . We manage 150…

operations-researchecommercetime-series-forecastingedelmandata-science

29 Apr

Thumbtack Engineering 9 min read

A practical look at how Thumbtack navigates evaluation for emerging AI experiences and what we’ve learned along the way. By: Shishir Dash , Director of Applied Science & Teja Venkat Kolli , Senior Applied Scientist Evaluating AI at Scale Introduction AI is reshaping how people interact with products, and Thumbtack is no exception. We’re introducing AI into more aspects of…

aiai-evaluationgenaiai-engineeringdata-science

15 Apr

Anjani Kumar 7 min read

The Race Against the Clock: Optimizing Supply Chain Capacity for Faster Deliveries — Part 1 (Capacity Management Series) In the hyper-competitive landscape of online retail, delivery speed is often the sole differentiator between a confirmed sale and an abandoned cart. For e-commerce giants, a sophisticated “ Promise Engine ” calculates the precise delivery date shown to a customer during checkout.…

stochastic-modellingoperations-researchdata-sciencecapacity-planningsupply-chain

24 Mar

Prakhar Sapre 8 min read

Expedia Group Technology — Data Workload‑aware routing for Trino Photo by Joseph Barrientos on Unsplash Trino — a fork of PrestoSQL — is a powerful tool in modern data analytics, enabling organizations to query large datasets quickly and efficiently. As a distributed SQL query engine, Trino provides fast, scalable insights without requiring data relocation. While Trino is robust on its…

trino-gatewaysqlanalyticstrinosdata-science

17 Feb

Benjamin Stieger 9 min read

Expedia Group Technology — Data Quickly identifying winning ranking models before committing to A/B tests Authors: Adam Woznica, Benjamin Stieger, and Stefania Ebli Photo by Il Vagabiondo on Unsplash Expedia Group ™ covers a portfolio of brands such as Expedia.com, Hotels.com, and Vrbo, that power lodging searches for millions of travel shoppers every day. In this competitive market matching users…

experimentationdata-sciencehypothesis-testingrecommender-systemsa-b-testing

27 Jan

Alyssa White, PhD 7 min read

Expedia Group Technology — Data Two roles one goal — understanding users better By Sophie Rabet and Alyssa White Photo by Samsung Memory US on Unsplash Quantitative User Experience (UX) Research, as a discipline, is growing rapidly. Quant UX Con 2022, the first ever general industry conference for the discipline, was organized with the expectation of about 200 attendees. After…

career-advicedata-scienceanalyticsux-researchquantitative-ux-research

6 Jan

Manisha Sudhir 6 min read

Expedia Group Technology — Data Science Empowering developers with seamless vector embedding solutions Photo by Daniela Cuevas on Unsplash Introduction Rapid advances in Machine Learning (ML), especially Generative AI, have increased the need for specialized capabilities like vector embedding similarity search. Vector embeddings are the numerical representations created by machine learning models which allow disparate inputs to be compared against…

machine-learningvector-databasemlsdata-science

4 Dec 2025

Sri Raghava Muddu 7 min read

Image Source: Google Nano Banana TL;DR LLMs struggle to summarize the thousands of reviews for a single product because of context window limits and conflicting opinions. The proposed solution, XL-OPSUMM, is a scalable framework that summarizes reviews incrementally (in chunks) to overcome these limits. Its key innovation is the Aspect Dictionary — a numerical scorecard that tracks the exact count…

ecommercelarge-language-modelsdeep-learningdata-sciencetext-summarization

10 Oct 2025

James Chan 6 min read

As a fast-growing home services platform, we heavily utilize machine learning to elevate user experience and improve business processes such as reducing spam, improving search results, and providing recommendations. In recent years, Generative AI has taken the world by storm as a powerful addition to traditional ML. We embraced this mega trend by incorporating LLMs into various areas of our…

data-sciencedatabricksgenaiinformation-securitymachine-learning

19 Aug 2025

17 Mar 2025

João Palmeiro 6 min read

Data scientists use different Jupyter notebooks every day — ranging from disposable ones for quick tasks to those shareable with clients. Over time, more and more notebooks accumulate, making it increasingly difficult to reuse them in whole or in part. To mitigate this problem and make the most relevant pieces of code quickly accessible to every data scientist, we developed…

jupyterlabpythondata-sciencejupytersnippet

2 Dec 2024

4 Nov 2024

Jeffrey Mew 2 min read

AI did not write this blog post, but it will make your exploratory data analysis with Data Wrangler better! Today, we’re excited to introduce our first step of integrating the power of Copilot into Data Wrangler. With this first integration of Copilot with Data Wrangler, you’ll be able to: Use natural language to clean and […] The post Announcing GitHub…

data sciencedata wranglerpythonvisual studio codeai

7 May 2024

Jeffrey Mew 3 min read

Today, we are excited to announce the general availability of the Data Wrangler extension for Visual Studio Code! Data Wrangler is a free extension that offers data viewing and cleaning that is directly integrated into VS Code and the Jupyter extension. It provides a rich user interface to view and analyze your data, show insightful […] The post Announcing Data…

pythonvisual studio codecsvdatadata science

28 Nov 2023

Roland Meertens 8 min read

A clustering-based approach to create deep learning datasets in a day Introduction Understanding what’s happening in an image is both an important task, as well as a costly one. In the last few years, the field of computer vision has greatly accelerated due to the advances in neural networks. At Bumble Inc., we see potential value in computer vision for…

data-sciencemachine-learningclusteringdeep-learningdataset

17 Mar 2023

14 Nov 2022

Deepak H R 5 min read

Primary author: Deepak H R Project guidance: Narasimha M MakeMyTrip experiments with multiple ranking recommendation systems to measure offline metric improvement and maximize online business or engagement metric lift. Data science systems, for example, use collaborative filtering, learning-to-rank algorithms, attribution models, debiasing techniques, embedding representation learning methods, shallow GNN methods, content-based representations, and lightGBM to Deep neural network architectures.

data-scienceneural-networksrecommendation-system

Vijay Yadav 6 min read

Primary authors: Vijay Yadav , Deepak HR Co-author : Narasimha 1. INTRODUCTION MakeMyTrip has multiple ranking/recommendation systems. We use learning to rank, sequence-based recommendation models, content or behavior representation-based algorithms, and collaborative filtering algorithms too. After the customer browses around, searching for hotels in city A, B or C, a substantial portion search for a single hotel and look at…

data-sciencemodel-selectioncontextual-banditreinforcement-learningdeep-learning

21 Sept 2022

Simone Spaccarotella 7 min read

How I learned to manipulate JSON data with Pandas on a Jupyter Notebook and deconstruct it to a DataFrame ready for queries. Image by author created from Jupiter photo by NASA and Pandas photo by Pascal Müller on Unsplash A bit of context first I started a self-study path to learn the theoretical fundamentals of Data Science and Machine Learning.…

data-sciencejupyter-notebookpythonpandaskaggle

21 Apr 2022

25 Oct 2021

Steve Dower 1 min read

Our friends at Anaconda have posted a joint announcement last week regarding the use of their repository from Microsoft cloud-hosted products. See the full announcement on their website. Today, Anaconda, Inc. announced a collaboration with Microsoft to enable customers to confidently access Anaconda’s curated library of open-source packages within Microsoft Cloud-hosted products and services, including […] The post Anaconda licensing…

azurepythonanacondadata sciencemachine learning

8 Jul 2020

Sid Unnithan 4 min read

The VS Code team is excited to announce releases of the Azure Machine Learning extension which aims to help you manage your core machine learning assets from directly within your favourite editor! The post Enhance your Azure Machine Learning experience with the VS Code extension appeared first on Microsoft for Python Developers Blog.

azureazure machine learningvisual studio codeazure machine learning extensiondata science

16 Apr 2019

Michael Droettboom 14 min read

Pyodide is an experimental project from Mozilla to create a full Python data science stack that runs entirely in the browser. We think it’s worthwhile to work on moving the JavaScript data science ecosystem forward, and that's why we built and released Iodide earlier this year. In the meantime, we’re meeting data scientists where they are by bringing the popular…

featured articlejavascriptdata scienceiodidepyodide

24 Jan 2018

4 Oct 2017

5 min read

Here at SoundCloud, we’ve been working on helping our Data Scientists be more effective, happy, and productive. We revamped our organizational structure, clearly defined the role of a Data Scientist and a Data Engineer, introduced working groups to solve common problems (like this), and positioned ourselves to do incredible work! Most recently, we started thinking about the work that a…

data sciencemachine learninganalyticsdata

21 Jun 2016

3 min read

With more than 125 million tracks from over 12 million creators heard each month on our platform, SoundCloud is uniquely positioned to offer listeners a full spectrum of music discovery. Classic hits, the latest releases, gems from underground talent and the best of what’s up-and-coming – all in one place. How can you make great content discoverable and available at…

announcementsrecommendation systemmachine learningdata science