Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Swiggy Bytes
Building a Robust Controlled Rollout System for Frontend at Scale
When you’re operating at the scale of a company like Swiggy, implementing a controlled rollout system is not just a nice-to-have — it’s a mandatory cog in the machine. Without this, a single bad release could result in a breaking change reaching 100% of your end users, leading to outages, frustrated customers, and increased churn. At Swiggy, where our customers are already Hangry, we simply cannot afford to take that risk.
A Swiggy Manager's Analytical Adventure
Swiggy's Analytics Manager, Aniket Kumar shares memorable experiences and learnings as he completes five years with the company. In a data-driven world, analysing numbers and trends is a must to make way for the right decisions and strategies. Five years ago, Aniket Kumar joined Swiggy fresh out of his graduation from IIT Delhi.
Pandas: apply, map or transform?
A guide to Pandas’ most versatile function As someone who’s been using Pandas for a few years now, I’ve noticed how many people (myself included) often resort to almost always using the applyfunction. While this isn’t an issue on smaller datasets, the performance issues caused by this become a lot more noticeable when working with larger amounts of data. While apply’s flexibility makes it an easy choice, this article introduces other Pandas' functions as potential alternatives.
Introducing PyDicom, its Classes, Methods, and Attributes.
PyDicom…Beyond Pixel Data If you are a Pythonista and you’re working with Medical Data, especially DICOM data, you’ve probably heard of the great python package PyDicom. In this post, you’ll learn the basics of this package. We’ll discuss PyDicom classes (DataSet, DataElement, Sequence) and some useful methods and attributes that you can apply to PyDicom classes. PyDicom is a pure Python package for working with DICOM files such as medical images, reports, and radiotherapy objects.
Time Series Forecasting with Feature Selection: Why you may need it
Speed up Forecasting while Preserving Performances When approaching for the first time a forecasting task, it’s a good practice to start adopting standard and baseline solutions. In the first part of the project, we must dedicate our time to understanding the business needs and conducting adequate explorative analyses. If we can’t wait to build a predictive model, the best option is to fit naive models.
Word Sense Disambiguation for Hindi & Python’s hindiwsd library
With all the advancements that have been made thus far in the field of Natural Language Processing (NLP) and Linguistics, you’d think intelligent systems would be capable of finding out the right meaning of a word used in a certain context. However, that is not the case, at least not in low-resource languages like Hindi and code mixed Hinglish, wherein much work is yet to be done.
6 Papers Every Modern Data Scientist Must Read
A list of some of the most important modern fundamentals of Deep Learning everyone in the field show be familiar with Data Scientist, Machine Learning Expert, Algorithm Engineer, Deep Learning Researcher — whatever your title might be, if using advanced concepts of Machine Learning is part of your career, then keeping up to date with the latest innovations is also a part of your everyday tasks.
Structure Your Data Science Project - The Double Diamond Model
The Double Diamond model prescribes divergent and convergent thinking for both the research and design phase. With up to 85% data science projects failing, structured design processes are necessary more than ever. Data Science takes place within the complex intersection of programming, mathematics and business. The proverbial unicorn is a master in all of these areas, yet in practice being a master in one domain and proficient in the others is the best you can hope for.
Fall in Love with Your Environment Setup: Vagrant Edition
NOTE: This article references the vagrant-python-setup repo Pyenv has seriously let me down.
How to Use cumsum() to Solve Python Optimization Questions
This very interesting Python interview question from Goldman Sachs is a good example of a large family of data science interview questions that concern optimization. Learn how the cumulative sum operator can be used to solve such questions. Image created by the author on Canva Minimum Number of Platforms The title of this question is Minimum Number of Platforms and it says that we are given a day worth of scheduled departure and arrival times of trains at one train station.
The New Benchmark for Question Answering over Knowledge Graphs - QALD-9-Plus
And the problem of multilinguality that the benchmark is aiming to solve For heterogeneous user groups (e.g., language, age), the ability to interact with web applications in the same effective way is one of the most important factors in the concept of “accessibility”. This includes Knowledge Graph Question Answering (KGQA) systems, which provide access to data and knowledge from the Semantic Web through a natural language interface.
Need Help Making Decisions? Ask Your Digital Twin!
Let’s face it: making decisions is hard. Just consider the following hurdles to overcome: You need to figure out how to actually evaluate decisions. What performance metrics truly matter, how would you rank or weight them? Once you know what constitutes the quality of decisions, you need to estimate how various decisions score on the defined metrics. The consequences of decisions typically reveal themselves only in the future. There is no instant feedback mechanism.
A Better mAP for Object Detection
ML TIPS & TRICKS / TIDE TL;DR: Your object detection model sucks and you want to improve it by leveraging better evaluation metrics… skip the introduction, and find out how or go directly to the Google Colab notebook for the code or here for the ClearML experiment log! False positives and false negatives are the main problems in object detection (source: Photo 6 Jets Parading Toward Clouds by Sajid Ali from Pexels with overlay by the author) Object detection is easy.
Predicting individual survival curves with Keras
Introduction Both in research and the industry, thereis an increasing interest in predicting individual survival functions, i.e. a survival probability function at any given time. Most of the existing methodologies for this task are either parametric or semi-parametric, while very few remain strictly non-parametric.
‘We are in this together’ - Here’s how your contribution is helping India battle the COVID-19 crisis
India is currently battling a gruesome second wave of the COVID-19 pandemic and as the country’s healthcare continues to be under pressure, Paytm has stepped forward to help in COVID-19 relief efforts. We are undertaking efforts on a war footing in this fight against COVID and have launched #OxygenforLife initiative through ‘Paytm Foundation’.
Predicting your next query even before you type!
A shopping journey store captures a typical customer’s shopping journey on Flipkart. Our Extract-Transform-Load (ETL) pipelines capture the search events and the corresponding product clicks from the shopping journey store and aggregate them for a period. This data becomes one input to a Content Generation Framework (CGF). We establish relations between the search queries and multiple related destination queries in the CGF.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Swiggy
Contact Swiggy, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack