DSC Croatia 2022
2022-05-10..2022-05-12
Zagreb, Croatia
as the organisers put it
DSC Croatia 22 is a Hybrid event happening from May 10th-12th in Zagreb. Conference is dedicated to the impact of data on Business & Society. Topics are: Data Analytics & Engineering, Data Strategy, Decision Intelligence, Ethical AI and AI for Good. Data Science Conference is one of the leading Franchises dedicated to Data Science & AI worldwide. It is a multidisciplinary conference with an abundance of talks, discussions, workshops and hands-on tutorials, connecting Business, Professionals and Academia in one place.
| title | author | length |
|---|---|---|
| NLP Solutions for infodemic management | Ana Mestrovic, Mladen Fernezir | 28m |
InfoCoV builds a multilayer pipeline for COVID-19 infodemic monitoring on Croatian social media: collected datasets include ~200k tweets and large news corpora… | ||
| The Ethos of Process in ML | Leanne Fitzpatrick | 39m |
Argues that machine learning fails when process is weak, not when tech is missing, contrasting CRISP-DM with a devops-style loop that must capture data bugs… | ||
| AI Ethics: The Trees that Conceal the Forest | Emmanuel R Goffi | 30m |
Argues that "AI ethics" is an ill-defined buzzphrase used as marketing and soft law to sell reassurance and geopolitical advantage, cites the EU's trustworthy… | ||
| Constrained Monotonic Neural Networks | Davor Runje | 30m |
Presents a concrete method to enforce monotonicity in deep nets by combining convex and concave activations inside a simple monotonic layer, producing… | ||
| Reducing Carbon Footprint in Smart Buildings with Data Science | Nemanja Milicevic | 12m |
A deployed system called Optimus Power uses historical sensor and weather data to build a thermal model and trains an agent with thermal model + reinforcement… | ||
| Why should data sets care about privacy,rule of law and human rights in at all | M.Robic | 33m |
Argues that datasets must be built with law and rights baked in: track the EU Digital Decade rules, map dataset uses to the AI Act risk categories, and budget… | ||
| Can we measure depression | Damir Mulc, Eda Jovicic | 28m |
Using 19 EEG channels and 10–15 minute steady‑state recordings, EEGs are cleaned with filtering and ICA plus Independent Component Label to remove blinks and… | ||
| ML App in the hospitality industry : optimization of HR management | Goran, Nebojsa | 32m |
Hotel chain Maestra builds an automated staff-planning web app for Amarin (280 rooms, 850 guests) that forecasts working hours and maps them to job categories… | ||
| Generate Insights, Not Excuses: How your data is slowing you down | Livio Bencik | 28m |
Argues that purposefully generating fresh, relevant data through experiments beats months of cleaning legacy logs, showing a workflow from expert-driven… | ||
| Data interpretation for B2B SaaS tools: how to bring informed business decisions | Marko Dragic | 25m |
Clicker scrapes roughly 400 retailers and telecom operators 2–4 times a day to produce near real‑time, structured KPIs, limits dashboards to 8–10 KPIs, embeds… | ||
| Semantic segmentation of tennis match videos | Mladen Canovic | 22m |
Platform segments pro matches by OCR on localized scoreboards and non‑pro matches by action recognition; scoreboard localization plus heuristics reconstructs… | ||
| Classifying the variety of customers online engagement for churn prediction | P.Simovic | 32m |
Proposes a mixed penalty logistic regression that blends absolute (median) and squared (mean) regularization to enforce sparsity and avoid overfitting on… | ||
| Disrupting Lead Generation through Artificial Intelligence | Arthur Jansen | 27m |
Dun & Bradstreet describes a production pipeline that fuses website text and images plus news and social signals, converts them to vectors with NLP CNN and… | ||
| Why is data important for European Space Agency? | Martin Mossler | 48m |
ESA provides open data from its Earth observation satellites (Sentinel) that anyone can access for free, but the raw output is multi‑layered and needs… | ||
| Writing scientific papers about data science projects | Mirjana Pejic Bach | 28m |
Gives a concrete four-step writing workflow—competence, course, composition, content—and shows how bibliometric analysis plus text mining on Web of Science… | ||
| Manufacturing optimisation & planning using ML platform | Nino Pozar | 27m |
Platform builds per-SKU demand models that automatically select the best algorithm per item, integrates historical plus contextual data, and exposes forecasts… | ||
| Big data in personalised medicine | Gordan Lauc | 38m |
Claim that genetics explains only ~12–20% of longevity and ~30% of complex disease drives focus to lifestyle-responsive biomarkers such as glycans; team-wide… | ||
| How we create and leverage Data Services in GitLab.com | Radovan Bacovic | 25m |
Walkthrough of how GitLab.com builds an Enterprise Data Platform using the GitLab product to dogfood its own pipelines, with concrete tooling and practices… | ||
| U-Net is all you need: applying the same AI approach for many different business domains | M.Fernezir | 27m |
U‑Net serves as a reusable backbone across medical 3D volume segmentation, short‑term radar nowcasting, document element detection and deployed selfie… | ||
| Improving Photomath’s math problem scanning with deep learning | Ivan Jurin | 30m |
Photomath replaces legacy on-device OCR with a cloud-deployed deep learning pipeline that moves from 2016 object-detection OCR to an end-to-end CNN+BiLSTM and… | ||
| adjust.me! - AI-Based Table Auto Positiong | Tomislav Krizan | 22m |
An AI pipeline classifies three posture categories (plus about 10 finer poses), measures joint distances using depth markers, and commands a retrofitted IKEA… | ||
| Panel discussion - Building Data Products | Davor Runje, Maja Vekić Vedrina, Smilja Plišić Velimirović, Andjela Culibrk | 49m |
Panelists argue companies must move from ad hoc analysis to measurable, production data products: examples include recommendation engines that lift conversion… | ||
| Building smarter ML and AI models and making them more accurate | David Akka | 33m |
Claims a SQL-based GPU platform called scream that reads from storage straight into GPU cores to avoid memory bottlenecks, runs terabytes–petabytes without… | ||
| Managing your Data Assets: The interview | Milos Milovanovic | 29m |
Company Things Solver describes two ongoing data governance projects: one cleaning product transaction tables, one ingesting semi‑structured HR and ATS feeds… | ||
| Digital footprints in credit scoring | Kristina Reicher | 35m |
E‑commerce logs plus a private credit bureau score train a plain logistic regression using 10 digital-footprint variables (device, email type, typing errors… | ||
| DSC Croatia 22 Aftermovie | 01m | |
DSC Croatia 2022 has been a blast!
60 Speakers
100+ hours of talks
500+ industry experts
25 countries
all in one place!
See you soon...
Change the… | ||
| Interview with – Martin Mossler | Martin Mossler | 25m |
Runs the ESA BIC Austria through Science Park Graz and says the incubator has developed roughly 300 companies, claiming it’s the largest in Austria; core work… | ||
| Interview with – Leanne Fitzpatrick | Leanne Fitzpatrick | 30m |
Explains concrete startup checks: assess data maturity (Financial Times maps subscriptions to customers, built a “breadth of reading” recommender to avoid echo… | ||
| Interview with – Mario Mrljic | Mario Mrljic | 16m |
Neos builds a data intelligence platform that indexes datasets, shows lineage, usage counts and simple reliability scores so business users can find and reuse… | ||
| Interview with – Marko Dragic | Marko Dragic | 11m |
Strategio builds Clicker, automated product-market intelligence that shows where every product sits across markets and competitors and reduces noise to focus… | ||
| Interview with – Kristina Reicher | Kristina Reicher | 12m |
Koyo's Consulting applies ML/AI to banking credit scoring and claims digital footprint variables like shopping cadence, email patterns and mobile device… | ||
| Interview with – Emanuel R. Goffi | Emanuel R. Goffi | 11m |
Claims that ethics is not universal, tracing work from worked on drones in 2005-06 to AI and arguing Western guidelines dominate and risk imposing a cultural… | ||
| Interview with – Arthur Jansen | Arthur Jansen | 07m |
Company sells B2B business signals and builds a new lead product that scores prospects from website content instead of just annual financials, letting models… | ||
| nothing matches | ||