symphony.is’ Post

❓ Can automated grid sampling improve efficiency in data collection? 🛰️ In their NEW blog, IDinsight’s Data Science and Engineering team members talk about grid-based sampling – a method that enables researchers to sample targets for surveys using geospatial data – and describe the tool they built to make grid-based sampling easier, and more efficient for our teams at IDinsight. 🔗 Delve into the blog here: https://bit.ly/3OYBDSG

What’s better than learning dataviz skills from our world-class expert speakers? Receiving one-on-one feedback on your own projects from them! Here’s what we offer at DataFest Tbilisi 2024: 👥 Share your project with us, and we'll book a feedback session for you! 🖼️ The finest DataViz projects will be showcased during the "Showcase Your DataViz" expo at DataFest Tbilisi 2024 for the whole audience to see. ✨ Get the chance to present your work to a wider audience and find new collaborators as you bring clarity to our chaotic world through data visualization. 🎟️ To upload your DataViz project, you need to have a ticket for DataFest Tbilisi 2024. If you haven't got one yet, grab it now with a 20% discount: https://shorturl.at/elENZ 💡 Keep in mind that the spots are limited, so don’t hesitate to register: https://shorturl.at/ES9SI

Well, this is big! Get a look into the HUB Oceans Ocean Data Platform - and get ready for a super exciting hackathon on digital twins! Digital twins of the ocean are super user centric and user friendly. Behind all that digital twins jazz are advanced technologies and abundance of data. Hub Ocean is our ocean community liason with the industries. Through the Ocean Data Platform they are facilitating interoperabilities on technical and human levels between industry, academia, and users. In this webinar we get to learn about both technical aspects as well as seeing some of the beautiful use cases. Come join us! PS. Blushing 😊 #digitaltwins #interoperability #ocean #iliadhackathon24

Thrilled to share that our Head of Data & Analytics will be discussing process optimization in data ingestion! He will also delve into the intricacies of training AI and ML models. This session promises to offer valuable insights into enhancing efficiency and leveraging advanced technologies. #DataAnalytics #AI #MachineLearning #ProcessOptimization

I'm thrilled to announce that, along with my teammates Oleg Ulukov and Yuval Zindani, we took first place at the data and machine learning hackathon held at Ruppin Academic Center! This competition brought together great people and minds in the field, and we're incredibly honored to have been recognized for our work. Our project tackled the challenge of sustainable route prediction using a massive dataset of 2 million entries. This data included starting and ending positions, dates, transportation methods, and travel times. Our goal was twofold: Shortest Path Model: To create a model that could analyze two positions and a date, and then predict the quickest route based on the provided information. Least Polluted Route Model: We also recognized that different transportation options have varying environmental impacts. So, we built a second model that, given the same inputs, could recommend the route with the lowest overall pollution footprint. Here's how we achieved this: Prediction with XGBRegressor: We leveraged the power of XGBoost, a machine learning library known for its effectiveness with tree-based models. We trained an XGBRegressor model to predict the travel time between each pair of locations in our dataset. Graph Creation with DiGraph: With these predicted times in hand, we constructed a directed graph (DiGraph) using Python's NetworkX library. This graph served as a map, where nodes represented locations and edges represented the connections between them, weighted by the predicted travel times. Shortest Path with Dijkstra's Algorithm: To find the quickest route between any two points, we implemented Dijkstra's algorithm. This widely used algorithm efficiently navigates graphs to identify the shortest path between any two nodes, considering the edge weights (travel times in our case). This hackathon experience was invaluable. Building upon my participation last year, where I secured fourth place, I was able to: Learn from Mistakes: I identified areas for improvement from my previous experience and addressed them effectively this year. Power of Graphs: I gained a deeper understanding of the utility of graphs in representing and analyzing pathfinding problems. The hackathon fostered a fantastic collaborative environment. My teammates, Oleg Ulukov and Yuval Zindani, and I constantly supported each other, maintaining a fun and competitive spirit throughout. We were fortunate to have the guidance of four professors who provided invaluable support and mentorship during the hackathon. A huge thank you to the organizers of the hackathon for putting on such a fantastic event, and congratulations to all the other participants! #RuppinAcademicCenter #HackathonWinner #DataScience #MachineLearning #SustainableRoutes #AIforGood #XGBoost #Dijkstra #NetworkX

Some interesting data here by Dezerv team.

Today I had the pleasure of attending this fascinating live event hosted by Data Innovators .🤯 It was eye-opening to see how data is transforming decision-making, not just in business, but in our everyday lives! Here are some key takeaways that resonated with me: 🕛 Timing is everything: Success can hinge on when we take action. Incremental improvements, tailored to our specific needs, are key to achieving results. 💪 Daily actions matter: Consistent effort, informed by data and minimized bias, drives the best outcomes. ⌛ Patience is a virtue: Systemic change takes time, and data helps us navigate the journey. 🌍 Data democratization: Data is no longer confined to the tech world. It's a tool for understanding our customers, our world, and ourselves. 📈 Real-time insights are crucial: The need for immediate data analysis is growing rapidly. 🚀 Data empowers personal growth: From informing our decisions to fueling AI, data is a powerful force in our lives. Ultimately, data empowers us to make more informed decisions, leading to better outcomes in every aspect of our lives. It's exciting to see how this field continues to evolve and impact the world around us. Data is transforming our world. Are you ready to harness its power? 🚀 #datadriven #success #dataanalytics #AI #decisionmaking #insights #innovation #ethicaldata #datainnovators

Our Paris Data Day for Investors is returning on 30 October! Join us alongside 100+ members of the alternative data community, where we’ll be diving deep into the hottest topics in the alternative data space, including: 🌐 What will 2025 look like for alternative data? 📉 Tackling alpha decay and the lasting value of alternative data 🤖 When machine learning and alternative data collide 💡 Vendor use cases and new product pitches To secure your place, email: 👉 events@neudata.co #neudatadataday #alternativedata #paris

Meet one of our data engineers, Hubert Liang, who is an expert at being able to transform data chaos into clarity ! 👨🏻💻 Read up about his experiences at Rocket Lab.

🎉 Let's Explore Nominal Data Together! 🎉 Hey, curious minds! Imagine you're in a colorful world full of different animals, each with its own name and type – lions, elephants, and giraffes, oh my! Just like that, nominal data is all about sorting things into groups. It's like organizing your toys by color or your friends by their favorite ice cream flavor. Simple, right? Nominal data helps us make sense of the world around us by giving everything a label, whether it's colors, shapes, or categories of things. So, join us on this adventure as we uncover the magic of nominal data and how it helps us understand the world in a fun and organized way! 🌈📊