Data Science Conference 4.0
2018-09-18..2018-09-19
Belgrade, Serbia
| title | author | length |
|---|---|---|
| What Makes a Good Function | Hadley Wickham | 47m |
Argues that good functions avoid surprises and fail early by using clear type rules, showing surprising c() behavior where combining factors, dates, and NULLs… | ||
| Conceptual Framework for entity integration from multiple data sources | Drazen Orescanin | 41m |
Proposes an iterative ordering algorithm that scores datasets by completeness/overlap/inverse/accuracy to decide which sources to merge first, implemented as a… | ||
| Using Data Riches: A Tale of two projects | Ajay Vinze | 41m |
Two applied projects show what data riches actually deliver: a semiconductor failure‑analysis system that builds an ontology and indexed retrieval layer and… | ||
| Why is Data Science still not a mainstream in Corporations | Sasa Radovanovic | 41m |
Argues that data science drives direct revenue not just cost cuts and lists concrete deployments at Telenor Serbia: a next-best-offer system using a 360°… | ||
| People, Technology, Culture: How to make Data Science work | Mario Meir-Huber | 44m |
Large enterprise data strategy argues for cutting platform complexity, moving legacy workloads from on‑prem to IaaS/PaaS and aiming for data science as a… | ||
| Data&AI in TomTom: How are are transforming mobility | PierLuigi Cassale | 32m |
TomTom explains that GPS and sensor fleets produce 18,000 times around the world per day and uses SVMs, random forests, convolutional neural networks and… | ||
| The Need for Explainable AI | Dorothea Wisemann | 28m |
Argues that explainability matters because AI moves into high-stakes decisions and gives concrete methods and results: a super-scalable structure-aware PDF… | ||
| ShopUp: why and how startups use free BI tool for product development | Sergi Sergiev | 33m |
In this talk we shall present Google Data Studio. Subtopics are:
- presenting why and how startups have to be fast using existing solutions
- overview of… | ||
| Machine Intelligence in Manufacturing Industry | Igor Mihajlovic | 33m |
Use of Machine Intelligence in manufacturing industry poses a special challenge due to a wide range of use cases, inherent complexity in data collection… | ||
| Predictive trading | Spela Poklukar | 30m |
Product uses 105 stock and 145 bond indices across ~18 years, engineers technical and macro features (returns, volatility, Sharpe), and predicts weekly for… | ||
| Applied Intelligence in SAP Digital Enterprise Platform | Heiko Steigerwald | 33m |
Describes why SAP customers embed analytics into core processes, outlines the Accenture Analytics on HANA Platform approach and its architecture choices, and… | ||
| Success case of modern algorithms applied in FMCG industry | Alberto Molinero Zaera | 28m |
Delivers a concrete FMCG deployment: builds 18 business-driven segments by training the sales force to label 5,000 points of sale, then scores ~150,000 venues… | ||
| 1984 Big Brother is Watching you (and helping with savings) | Tomislav Krizan | 45m |
A home-level analytics stack captures device traffic (including PLC over powerline to keep data local), funnels events into a message queue and stream… | ||
| Deep Attention Model for Triage of Emergency Department Patients | Djordje Gligorijevic | 32m |
A deep model predicts the number of ED resources a patient will need by combining structured fields and free‑text nurse notes, using word attention over… | ||
| Building end-to-end computer vision solutions from deep learning models | Vanja Paunic | 33m |
Microsoft shows how to turn ImageNet-scale research into usable pipelines using the Microsoft Cognitive Toolkit, Custom Vision Service and Azure Machine… | ||
| Supporting B2Bsales forecasting by machine learning | Mirjana Klajic Borstnar | 30m |
B2B sales forecasting is framed as a binary classification problem built with CRISP-DM and action design research, trained on 44,448 cases with 22 features… | ||
| Implementation of genetic algorithm in problem of processing GPS data | Marko Nikolic | 27m |
Claims a genetic algorithm with dynamic time warping and dynamic programming reconstructs sparse vehicle GPS to map links, provides Python code, and beats… | ||
| Hidden Biases In Data: Moving Beyond Black Box Models | Marko Jevremovic | 33m |
Built a behavior model that simulates a full user population (not an average) to reproduce cohort retention and session patterns, sampling sessions with a… | ||
| Ease the pain of Travel Refunds with AI | Katarina Milosevic | 29m |
Generali replaces SAP scanning with a Telegram bot that accepts smartphone photos, then classifies receipt type with TF-IDF + image analytics and extracts… | ||
| Machine Learning in News Media: Case study 24sata.hr | Marko Velic, Enes Deumic | 36m |
Styria.ai builds tag cleaning, recommenders and personalization for 24sata.hr, claiming concrete lifts: merged ~50,000 legacy tags down to ~8,000 to simplify… | ||
| Extracting keywords from texts | Sanda Martincic Ipsic | 31m |
Constructs a word co-occurrence network and ranks nodes by average edge weight rather than linguistic features, implemented in Python with NetworkX as SBKE… | ||
| Segmentation & classification of embryo videos in in-vitro fertilization | Stanko Kuveljic | 33m |
Pipeline segments embryos with U-Net segmentation trained on OpenCV-derived masks and achieves near‑perfect cropping, then learns image embeddings with a… | ||
| What is the Next in Data Science and Business Intelligence Practice | Petar Kocovic | 35m |
The latest technological advances in data processing, business analytics, and digitization will reshape the business environment increasing the business… | ||
| Ethics and Data Science | Milos Solujic | 31m |
Starts from concrete scandals — Facebook and Cambridge Analytica, Equifax, China’s social credit experiments — then argues current fixes (GDPR, corporate… | ||
| Enabling data-driven development for autonomous driving at BMW | Miha Pelko | 30m |
BMW ingests multi‑terabyte car logs (several TB per car per hour, tens of cars → petabytes) into a dedicated Hadoop cluster, copies SSDs via buffer stations… | ||
| SAS an open ecosystem for Artifical Intelligence | Dean Zouari | 01h 20m |
SAS Viya positions an enterprise analytics engine that runs models developed in Python or R or via a drag‑and‑drop GUI and deploys them anywhere from a laptop… | ||
| New Data Science Framework for Analysing and Mining Big Data | Charith Silva | 27m |
Proposes a stepwise framework that claims to reduce wasted effort by forcing problem definition, requirement gathering, then data acquisition, fusion… | ||
| Humanoid robots in retail: fad or trend | Anita Schmid | 24m |
Migros deploys 6 Pepper humanoids in a mall as concierge and entertainer: conversation, dancing, selfies, high‑fives, map directions and a live call to the… | ||
| Accelerating PostgreSQL Full Table Scan OLAP queries | N. Krgovic, A. Dragacevac | 35m |
Tests use PostgreSQL on AWS against a generated 165 million rows / 22 GB dataset and three OLAP queries; a columnar engine cuts disk I/O by about 30% less disk… | ||
| Power of big data and data science in service of excellent customer experience | A. Mandic | 27m |
Built a Big Data pipeline called IPI solution using Hadoop/HBase/Hive/Kudu, MapReduce and Spark ingesting up to 40–50 TB to monitor HFC and Wi‑Fi devices… | ||
| One day with Redshift | Bojan Sovilj | 23m |
Amazon Redshift setup, tuning and a real product demo: data lands on S3 (Athena for ad hoc CSV queries), Kafka handles streams, Power BI visualizes a “smart… | ||
| Data at scale: How to deal with small challenges when they become massive | A. Djurka | 34m |
Lazada (Alibaba Group) builds a centralized data platform that ingests everything in real time, enforces strict naming and a common data model, and exposes… | ||
| Building an recommendation system for IPTV | Tomislav Hlupic, Iva Soric | 32m |
A production IPTV recommendation pipeline built on a fast streaming stack uses Kafka for ingestion, Vertica for storage, Spark (PySpark) with ALS matrix… | ||
| Automatise everyday work | Sara Krk | 20m |
Team builds an automated A/B reporting pipeline that turns terabytes of event data into one-line-per-user user aggregates, runs nightly with a daily job and… | ||
| Let's play together: Collaborative Data Science | Mario Annau | 24m |
Companies often produce duplicated, fragile code instead of reusable libraries; R’s ecosystem has 13,000 CRAN packages but roughly single-author packages… | ||
| How to Prevent Algorithm-Porn | Nemanja Radojkovic | 31m |
Algorithm‑porn means adding complexity for ego not outcome and it kills projects through time and cost overruns and churn; a concrete win is stepping down from… | ||
| Data science vs real world: friends or foes | Pavle Kecman | 32m |
Built a Bayesian network to estimate evolving bodily‑injury reserves and a Flask UI, then add an OCR + document classifier (CNN with word embeddings) and… | ||
| A new way to profit: Predictive analytics and dynamic pricing | Srdjan Mladjenovic | 33m |
Dynamic pricing framework that scrapes competition with crawlers, recognizes competitor strategies, runs per-listing booking-probability ML models and… | ||
| How Data Science can empower your Sales and Marketing | Darko Marjanovic | 28m |
Retail case with Planeta Sport shows a working pipeline: ingest POS and ERP plus online data, anonymize for GDPR, run exploratory cleaning, produce… | ||
| The Challenges of Building a Personalized Recommendation System in E-Commerce | P. Poznic | 29m |
Built a personalized recommender for a Serbian e-commerce site from scratch using both content-based filtering and collaborative filtering with ALS matrix… | ||
| How to Start a Career in Data Science: Tips & Experiences | Nikola Radojkovic | 32m |
Claims an end-to-end starter path: spend 70% of project time on analysis, pick relevant sources, model as star schema, and build ETL mappings that validate and… | ||
| National Qualifications Frameworks in the age of data: what is in it for me | M. Balkovic | 32m |
National Qualifications Frameworks claim practical value in over 150+ countries and function either as static documentation or active reform levers; Croatian… | ||
| GDPR Impact | Aleksandar Ugljavarevic | 32m |
Covers concrete post‑May 25 GDPR effects: explains extraterritorial application (applies by offering goods or monitoring EU residents), cites CNIL inspections… | ||
| Open Data in Serbia: Status Quo and Future Perspectives | Sanja Nasevski | 30m |
Serbia launches a National Open Data Portal and passes the law on e‑government (April 2018), with 26 state bodies, 107 data sets, 362 data resources already on… | ||
| Importance of R-Ladies Initiative in DS Community | Tatjana Kecojevic | 18m |
R-Ladies Global grows from a meetup to a network in over 120 cities across 35+ countries, counting around 30,000 members and 7,000 Twitter followers; it uses… | ||
| Legal framework for Initial coin offerings (cryptocurrencies) | Dragan Maravic | 29m |
Timeline of ICOs and regulator positions across SEC ESMA BaFin and national bodies with concrete takeaways: regulators treat tokens case by case, utility vs… | ||
| TelCo Network Analytics & Customer Experience Management on top of Data Lake | G. Pavlovic | 26m |
Vip Mobile builds a small, on‑premise data lake that ingests CDRs, billing, CRM and OSS data to run two production apps: Network Analytics that gives real‑time… | ||
| Impact of GDPR on data mining and predictive analytics | Djordje Krivokapic | 34m |
This talk will be somewhere between academic and business talk. As an academic, I will explain the broad context of privacy and data protection related to data… | ||
| Can AI cause the end of the human race | Marko Bastovanovic | 31m |
Covers specific milestones and risks: chess, Go and Atari agents learn by reinforcement learning through tens or hundreds of thousands of self-play episodes… | ||
| Are public institutions ready to open their Data for wider use | Blerina Ramaj | 30m |
ACTION SEE’s Regional Openness Index covers 645 institutions across six Western Balkan countries and scores roughly ~30,000 indicators to track open data… | ||
| nothing matches | ||