The Fifth Elephant 2019
2019-07-25..2019-07-26
Bangalore, India
[The Fifth Elephant 2013, The Fifth Elephant 2015, The Fifth Elephant 2016, The Fifth Elephant 2018, The Fifth Elephant 2019, The Fifth Elephant 2020, The Fifth Elephant 2023 Monsoon, The Fifth Elephant 2025 Winter Edition, The Fifth Elephant Pune edition 2026]
as the organisers put it
The Fifth Elephant a community of ML Engineers, data scientists, platform engineers and practitioners from the data ecosystem.
who it's for
data engineers, machine learning engineers, platform engineers, data scientists, engineering managers, security engineers
topics
large-scale event pipelines; production feature engineering platforms; similarity search with FAISS; RedisAI model serving; streaming high-throughput analytics; hierarchical recommendation systems; schema evolution for pipelines; data privacy and PII encryption; probabilistic data bias correction; real-time social feed generation; assistive Indic language translation; fraud detection at scale
| title | author | length |
|---|---|---|
| State of Data Science & Machine Learning | Peter Wang | 38m |
Claims that packaging and tooling drove Python's adoption for data science supported by concrete projects and usage numbers: a self-contained Conda packaging… | ||
| Age of AI Ops | Nitin Gupta | 33m |
We look at the evolution and rise of AI Ops. AIOps is the technology solution leveraging machine learning and data analytics to help automate how we react to… | ||
| 7 steps to build-your-own data pipeline - for day 1 of your startup | Kumar Puspesh | 32m |
A cost‑sensitive startup pipeline that aims for immediate, row‑level access builds a thick client called squirrel then a file injector badger in Go and uses… | ||
| Leveraging Power of Analytics for Martech | Jacob Joseph | 45m |
Marketing Technology has undergone a technological revolution over the past 10 – 15 years. Today marketers are able to track the smallest of digital footprint… | ||
| Contracts, Schema Evolution in Data Pipelines | Agam Jain | 30m |
This talk is about sharing our learnings and some best practices we have built over the years working with massive volume and every changing schema of data… | ||
| Why data privacy is critical for robust data management? | Peter Wang | 20m |
Argues that data is radioactive waste: collect less, expire what you store, and avoid copying raw stores by running algorithms where data lives; demonstrates… | ||
| A journey through Cosmos to understand users | Avinash Ramakanth | 19m |
The topics we will be covering in this talk: 1. Introduction - Briefly provide business context to appreciate the need to solve this problem, and challenges… | ||
| The final stage of grief (about bad data) is acceptance | Chris Stucchio | 40m |
Practical recipe: write a probabilistic model of how reality becomes the recorded rows and infer its hidden parameters. Uses PyMC to infer a ~10% data loss… | ||
| Feed generation at ShareChat | Ayush Mittal | 32m |
ShareChat serves 85M monthly active users and ingests about 1M new posts daily, so feed generation combines a popularity bandit, autoencoder long‑term… | ||
| Analysing high throughput data in real-time | Namit Mahuvakar | 29m |
Introduction About Hotstar Stream Processing @Hotstar What is Stream Processing and Why was it required Problems that lead to usage Video Player Metricing… | ||
| Taking deep learning to production with RedisAI | Sherin Thomas | 34m |
RedisAI is a Redis module that adds tensors & graphs as Redis data types and executes models on CPU and GPU using PyTorch TensorFlow ONNXRuntime backends while… | ||
| Similarity Search for Product Matching @ Semantics3 | Abishek Bhat | 37m |
Semantics3 reframes deduplication as similarity search, trains a Siamese network with a boolean match label to embed products, and swaps Elasticsearch for… | ||
| Demystifying Social Network Analysis (SNA) | Sandeep Khurana | 41m |
Five case studies show concrete claims and tools not platitudes: data collection uses Python and Twitter APIs with 30–40 million tweets for the 2019 election… | ||
| Data Security for startups | Shadab Siddiqui | 24m |
Claims a repeatable startup-ready framework: encrypt all PII across legacy databases and analytics, lock down MySQL behind a proxy with MFA and query logging… | ||
| Improving product discovery via Hierarchical Recommendations! | Neha Kumari | 29m |
A recommendation engine’s primary goal is to surface personalised & relevant content to the user, content which satisfies explicit intent as well as… | ||
| How to build blazingly fast distributed computing like Apache Spark In-house? | Upendra Singh | 20m |
We at ClustrData are building extremely large scale, extremely cost sensitive analytics solutions for our end user. Being cost sensitive is of utmost… | ||
| Technology to counter misinformation/disinformation | Pratik Sinha | 40m |
A fact‑checking pipeline exists: a small nonprofit builds an Android app that matches images and videos to a database using PHash and MD5 checksums, returns… | ||
| ADAM - Bootstrapping a Deep Neural Network Sequence Labeling Model with minimal labelling | Shashank Jaiswal | 43m |
ADAM bootstraps NER for noisy product titles by generating weak labels from a sparse Knowledge Graph, matching ~1M stock items and retaining 8,000 weak labels… | ||
| Anatomy of a production ML feature engineering platform | Venkata Pingali | 45m |
Claim: feature engineering becomes its own production problem once features explode and run daily; Scribble builds a platform (Enrich) that tracks git commits… | ||
| Solving the vehicle routing problem for optimizing shipment delivery | Venkateshan K | 39m |
Variant of capacitated VRP with time windows, implemented as a custom solver because off‑the‑shelf OR‑Tools gives overlapping, elongated routes. Solution uses… | ||
| An open Assistive translation framework for Indic Language | Deepthi Chand | 12m |
India is a land of many languages. There are 23 official and much more unofficial languages prevalently used in day-to-day conversations. Unfortunately… | ||
| [Flash talk] Dynamic autosuggestions in search - Myntra | Myntra | 05m |
-- no description -- | ||
| [Flash talk] Fraud detection at scale using AI @ Razorpay | Razorpay | 06m |
Razorpay captures billions of events, extracts 200+ parameters into 300–400 features, and claims real-time fraud decisions within 200–300 ms. Features include… | ||
| [Flash talk] Labelling conversations in a sales CRM @ Freshworks | Freshworks | 09m |
-- no description -- | ||
| [Flash talk] MUDPIPE - Malicious URL Detection for Phishing Identification and Prevention | Arjun BM | 05m |
Social engineering is one of the most dangerous threats facing every individual and modern organization. Phishing is a well-known, computer-based, social… | ||
| [Flash talk] Enriching deterministic attributes with probabilistic attributes @ Affinity answers | 05m | |
-- no description -- | ||
| nothing matches | ||