+359 888 400 290
Beginners Guide how to Set up Superset (Opensource BI platform) on EC2 AWS instance

Beginners Guide how to Set up Superset (Opensource BI platform) on EC2 AWS instance

Why SuperSet?     Superset is a data exploration platform designed to be visual, intuitive and interactive, the main objective is to slice, dice and visualize data easily. It is open-source BI platform which can be deployed on every virtual server with no usage costs. Some of the main advantages are: it is maintained by Apache foundation and supported by AirBnB  Many visualization and ability to edit the code Support geolocations and uses mapbox Able to cache data for dashboards visualizations Admin panel available with very detailed settings  Able to access many SQL and NoSQL databases Easy and friendly user interface According to GitHub repo, Superset is currently being used by Airbnb, Twitter, GfK Data Lab, Yahoo!, Udemy and many others. We at ShopUp decided to give a try of that great platform and noticed that as products driven by the community, sometimes there is missing documentation. We have met some difficulties in setting up the platform on EC2...
Data preparation steps for Data Science or AI project in eCommerce or Retail

Data preparation steps for Data Science or AI project in eCommerce or Retail

Background Do you have tones of data and probably you want to take advantage of Data science and AI which are slowly but surely coming to the retail and ecommerce sector and these businesses are constantly generating huge amount of data. Before going into any modeling or data analysis each observer need to prepare the data in a way that machines can work with it. We decided to write an article about main approaches for data preparation of categorical variables called data encoding mainly observed in survey data. What data preparation means? Computers like variable as numbers therefore all textual values need to be presented in their numerical equivalent in order to be used for machine learning algorithms and deep learning neural networks. Simply they don’t like text. Here is an example. We have variables like: “Brand of car” with values “Mercedes”,”BMW” or others “Retailers Name” with values like “Kaufland”, “Metro” or “Mr.Bricolage” . “Sex” – “Male”, “Female” and many others...
Recommender systems in Retail 2019: Overview and Use case

Recommender systems in Retail 2019: Overview and Use case

 A Retail Case study about implementing recommender systems developed during the Summer School of Research Methods In summer 2019, some of the ShopUp team took part in the Summer School of Research Methods. The 7-day event was organized by several members of Data Science Society and academia representative from Sofia University, UNWE and Technical University Sofia. There were more than 10 lecturers and about 30 participants from different companies, organizations and universities. Among them were experts, researchers, PhD candidates and masters students. Each day the program started with presentations or workshops followed by allocated time for a Capstone project (a project which aims to capture what we’ve learnt). The workshops combined practice and theory in the area of maths, statistics, neural network, reinforcement learning and etc. The Capstone project was mandatory for each participant and there were three different cases to select from.    We at ShopUp decided to open-source this project work and share it with the community. The code we created is...
ShopUp Now Combines Data from Door Counters, Wi-Fi Routers, and Mobile Apps into an All-in-one Customer Analytics Platform for Malls and Shopping Centers

ShopUp Now Combines Data from Door Counters, Wi-Fi Routers, and Mobile Apps into an All-in-one Customer Analytics Platform for Malls and Shopping Centers

During the last 3 months ShopUp Customer Behavior Analytics platform has focused to malls and shopping centers, finalized the product, start on-boarding new customers  and generate constant revenue. Below you can read more about our progress. Business development: The ShopUp platform now offers an all-in-one solution for Malls and Shopping centers. We’ve created a complete tailored solution where we combined data from Door Counters, Wi-Fi Routers, Mobile Apps and other hubs into an all inclusive Customer Behaviour Analytics Platform. Now Mall owners, marketers, and analysts can see the data in one place and make decisions based on 360 degree view. 12 Malls have been on-boarded to the new platform and 20 more are in the pipeline. We started generating recurring revenue stream. We were part of the biggest Retail Conference: NRF in New York —  where we met great people and learned a lot about the newest trends in the industry. Product Updates Router Integration: ShopUp has been integrated and...
ShopUp is Now Scalable

ShopUp is Now Scalable

In the last 2 months we’ve done a lot of progress with our product and business development. We’d like to share with you where this journey took us: Product Updates Firmware Upgrade We improved the performance of the ShopUp sensors by upgrading the firmware. The amount of  data we’re now gathering have increased by more than 5 times. Also, we found a way to install the firmware directly on customers’ routers. We support more than 1,000 devices. That means we are now able to launch ShopUp remotely, without the need of physical installation on site within less than 24 hours. That is a huge advantage in terms of scalability. HeatMap We introduced a stable 2.0 version of the HeatMap where data visualization has been much improved compared to the previous version. The HeatMap is now based on an improved  mathematical model. Prediction Models Prediction models can now be generated based on ShopUp sensors and data integration with door counters,...
ShopUp September 2016 Update: Traction, New Partnerships and More

ShopUp September 2016 Update: Traction, New Partnerships and More

ShopUp has been busy this spring-summer and we have managed to have both great vacations and a lot of work done. Below are the highlights. Two global players joined teams with ShopUp Getting the wheel rolling is a big challenge for every startup. Thanks to the efforts and charms of the whole team, we’ve got our first 2 big paying customers from Bulgaria: A French home improvement and do-it-yourself goods retailer where we help them to locate the customers inside the stores and establish the hotspots for better product placement, and A British multinational retailer where we partner with one of the most innovative retail marketing agencies to offer near-by customer targeting. Both projects helped us introduce new functionalities to the platform and expand our understanding of customer issues and where our solution would fit best. We partner with great companies Earning the trust of partner companies is both reassuring that our idea is worth it and supportive for the process...