NEOZO AI Meetup × ClickHouse: How Modern Data Platforms Power AI
Every AI system is only as good as the data platform underneath it. Behind every agent, copilot, and LLM feature sits a growing layer of high-value data: traces, embeddings, evaluations, feature pipelines, and real-time analytics that decide whether your AI actually works in production.
Join NEOZO Cloud and ClickHouse for an evening in Bangkok exploring how modern data platforms power AI, from real-time ingestion and vector workloads to observability for LLM applications.
🗓️ Agenda:
6:00 PM: Registrations Start
6:00 PM - 7:00 PM: Registration and Networking
7:00 PM - 7:20 PM: Talk 1 - The AI-Ready Data Lakehouse: Scaling Intelligence While Optimizing Costs by Maximilian (Max) Simmoteit @ Neozo Cloud
7:20 PM - 7:40 PM: Break
7:40 PM - 8:00 PM: Talk 2 - ClickHouse for Feature Engineering in FinTech by Alua Magavyanova, Fraud Data Scientist & Risk Data Analyst @ Yusr Fintech, Dubai (previously Kaspi.kz and Fingular Fintech)
8:00 PM - 9:00 PM: Networking
If anyone from the community is interested in sharing a talk at this or future events, complete this CFP form and we’ll be in touch.
_____________________________________
🎤 Session Details: ClickHouse for Feature Engineering in FinTech
"ClickHouse was more than an analytical database in our workflow—it became the foundation for feature engineering in production machine learning.
In this talk, I'll share how we used ClickHouse to build and iterate on thousands of features for risk analytics in a fintech environment. These included transactional behavior, device intelligence, geolocation, session analytics, graph-based relationships, deduplication, internal credit history, and other large-scale analytical datasets.
I'll show how ClickHouse enabled rapid experimentation, efficient feature generation, and large-scale analytical workflows that supported both fraud detection and portfolio risk models. Rather than focusing on infrastructure, this session presents a practitioner's perspective on using ClickHouse for feature engineering and machine learning.
The talk will include practical examples, lessons learned, and challenges encountered while working with production-scale data."
Speaker: Alua Magavyanova, Fraud Data Scientist & Risk Data Analyst @ Yusr Fintech, Dubai (previously Kaspi.kz and Fingular Fintech)
I'm a Data Scientist and Risk Data Analyst with 5+ years of experience in fintech. Throughout my career, I've worked on feature engineering and machine learning for fraud detection, credit risk, and portfolio analytics. I enjoy solving complex data problems with SQL, Python, and ClickHouse, and I'm excited to share practical lessons from building ML solutions in production.