Conf42 Machine Learning 2026
2026-02-19
-- online --
[Conf42 Machine Learning 2021, Conf42 Machine Learning 2022, Conf42 Machine Learning 2023, Conf42 Machine Learning 2025, Conf42 Machine Learning 2026]
| title | author | length |
|---|---|---|
| ISO 42001 Required Documentation Artifacts for Beginners | Aleksandra Drobnjak | 45m |
States that 16 required documentation artifacts (CLP SOPI) are enough for an auditable AI management system, backed by 38 controls across nine objectives and… | ||
| Orchestrating Agentic State Machines with LangGraph | Rajeshwari Sah | 56m |
Prototype implements a 4-agent pipeline—transcription, structured extraction, summarization to SOAP, and a consistency checker—orchestrated as a LangGraph… | ||
| Governing Data Sovereignty in Distributed Multi-Cloud ML Systems | Sapna Pillai | 09m |
Multicloud ML faces three major challenges: lawful data residency, full auditability of data movement, and inconsistent regional laws (GDPR, US CLOUD Act… | ||
| Machine Learning for Adaptive, Self-Optimizing Systems | Aditi Namdeo | 12m |
Claims RL drives adaptive decision making while predictive models and anomaly detection cut failures: reinforcement learning, predictive maintenance, and… | ||
| Next-Generation AI Agents: Orchestrating Technological Evolution | Alex Vyatkin | 18m |
Claims that agents built on minimize expected free energy (active inference) need far less data and compute than LLM stacks, solve the exploration–exploitation… | ||
| Building Secure Backend Services with AI Agents | Marat Kenzhebulatov | 11m |
An engineer demonstrates that prompts alone fail and recommends containing agents in a docker sandbox with a restricted filesystem and command whitelist after… | ||
| Hybrid RAG–LLM Framework for Supplier Risk Intelligence | Sujith Vadakkepati | 23m |
Presents an implemented RAG+LLM pipeline that retrieves ERP records plus external news, regulatory and ESG signals, reasons over that evidence, and emits… | ||
| LLM Agents for Site Reliability | Sumit Kaul | 25m |
Claims a production-tested, human-in-the-loop architecture that ingests multi-source telemetry (logs, traces, metrics, deploys) to output situational… | ||
| Maximizing Credit Card Profitability with ML–Driven CLV | Avaneendra Kanaparti | 34m |
Uses AmEx experience and peer-bank practice to build CLV that predicts future spend, revolving amount, payment reliability, and default probability and drives… | ||
| The Role of Machine Learning in Today’s Payment Ecosystems | Balakumaran Sugumar | 37m |
Claims production ML cuts merchant onboarding latency by ~90% faster onboarding, reduces manual reviews by ~75%, and improves risk detection by ~40%… | ||
| Pricing, Supply, A/B and Switchback Testing in FoodTech | Sergei Nasibian | 19m |
Argues that delivery fee sits at a revenue sweet spot because raising price increases per-order revenue but reduces orders; local demand elasticity is… | ||
| Structural Intelligence for Telecom Towers in the 5G Era | Sudarshan Kasera | 14m |
Argues that scaling structural analysis from individual sites to portfolios of up to 40,000 towers requires centralized data integration, not just PDFs, and… | ||
| Performance Optimization in High-Volume Transaction Systems | Vivek Kumar | 14m |
Shows an end-to-end ML pipeline that ingests telemetry (CPU, latency, request rate, thread usage) and uses LSTM, anomaly detection and regression models to… | ||
| Beyond Surveys: Real-Time User Satisfaction Prediction | Abhinay Kumar Reddy Seella | 13m |
A system called DNPS predicts session-level Net Promoter Score from telemetry, behavior and text using a hybrid stack of gradient-boosted trees, sequence… | ||
| Unifying Online and Offline Worlds | Ashutosh Verma | 06m |
A machine learning pipeline that merges website, social, email and point‑of‑sale data into a centralized store and uses probabilistic matching plus… | ||
| Making recommendations explainable | Lev Fedorov | 16m |
Replaces opaque user embeddings with a list that stores positive publication IDs and builds a lookup mapping each positive to its candidate set; filters pairs… | ||
| Beyond Send-Time Optimization | Murthy Chandrapaty, Chakravarthy Kalva | 25m |
Claims an AI decisioning layer outperforms classic send‑time optimization by choosing send/defer/skip actions rather than just the statistically “best” minute… | ||
| Hands-On Tutorial for Defining and Scoping Recommendation Systems | Rohan Mitra | 12m |
Defines a five‑pillar “modern AI spec” and shows a live rewrite of a broken smart‑reply PRD into a measurable plan: behavior contract with good/bad canned… | ||
| Zero Service Desk: Applying Machine Learning for Autonomous IT Support | Anu Arora | 28m |
ServiceNow describes a program that uses the ServiceNow platform as a single entry point plus ML classification intent anomaly detection to cut incident volume… | ||
| ML-Powered IoT: From Warehouse Data to Prod Intelligence in Real Time | Dinesh Garg | 29m |
Warehouse systems produce multiple terabytes of noisy sensor logs and show examples like 10,000 failed transactions per month, so the claim is: get 80–95%… | ||
| Transforming Inventory Forecasting with Production ML | Pallab Haldar | 16m |
A production reference architecture on Azure ingests ERP/POS/IoT into a unified data lake with Azure Data Factory and runs models in Azure Machine Learning… | ||
| Stop Failures Before They Happen: Gradient Boosting | Pavel Solikov | 16m |
Predicts SLA breaches after the first task using a lightweight 11-feature vector and runs inference inside Prefect UI to attach a risk score that can abort or… | ||
| Automating Continuous Compliance for Scalable, Sustainable SaaS ML | Pooja Ranjan | 24m |
Oracle Cloud builds end-to-end ML tooling: touchless CI/CD using GitLab/Bamboo and Terraform, deployment to Nvidia GPUs and bare‑metal, and automated… | ||
| Building Scalable, Observable MLOps Systems on Google Cloud | Ancilia Dmello | 23m |
Blueprint for running models on Google Cloud with concrete pieces: use Vertex AI for training and experiment tracking, Dataflow for real‑time feature… | ||
| AI Readiness Blueprint for Enterprises | Kiran Ramanna | 22m |
Claims that 80% of AI projects fail and 88% of pilots never reach production anchor a practical five‑pillar readiness model with stage definitions and… | ||
| Why Good Models Fail After Deployment | Oleksandr Pyvovar | 25m |
Claims that 87% of data science projects never reach production and Zillow loses ~\$1B when pricing models fail; real failures include Google’s diabetic… | ||
| Taming Data Skew in Production ML Pipelines | Srihari Godleti | 24m |
Roku production Spark pipelines suddenly stretch from under an hour to ~3 hours because 95% of tasks finish quickly while one executor processes ~10x the… | ||
| From Reliable Models to Resilient ML Platforms | Srinivas Talasila | 25m |
Explains concrete platform choices and operational controls: uses IBM Cloud SoftLayer bare‑metal and virtual compute with a global backbone, recommends… | ||
| Protecting PHI in Machine Learning Development Environments | Reshma Vemula | 06m |
Development environments account for 51.3% of reported healthcare breaches, with tens of thousands of records exposed per incident, and using real PHI drives… | ||
| IAM and Privileged Access Foundations for Secure ML Platforms | Neha Asthana | 12m |
Describes an implemented identity stack that ties HR as the authoritative source to automated provisioning, role changes, deprovisioning and rehire workflows… | ||
| Machine Learning–Driven Third-Party Risk Management at Scale | Sagar Sudhir Behere | 22m |
Rearchitects TPRM into an ML-driven pipeline that automatically ingests continuous feeds, uses NLP evidence extraction to pull verifiable control sentences… | ||
| ML–Driven Compliance Engines for Zero Trust Security | Sudheer Kumar Aluvala | 10m |
A production architecture uses a closed-loop ingest→train→predict→feedback pipeline that pulls endpoint telemetry, user behavior and cloud threat feeds to… | ||
| Building GenAI That Doesn't Cost the Earth | Mohamed Najaaf | 20m |
Model training compute grows ~350,000× from 2014–2024 and data center demand may hit ~800 TWh by 2030 while Goldman Sachs projects 60% of that rise met by… | ||
| Unified Perception: Models for Autonomous Driving | Sowmiya Narayanan Govindaraj | 08m |
Unified perception replaces fragmented stacks with a single model that shares a backbone, cross-model alignment networks and temporal fusion and uses… | ||
| Use ML to Predict Delivery Time and Improve Code Reliability | Tim Markin | 12m |
Built a predictive pipeline that extracts features from Git history, runs RAG + LLM reasoning, and outputs time estimates with confidence, risk scores and… | ||
| nothing matches | ||