Cloud DevOps: Inventory Management in the Cloud

Struverse specializes in Cloud DevOps, adept at deploying systems into the AWS public cloud to effectively reduce cloud computing costs for businesses with a large number of users. Our work, including projects for major telecommunications providers in Mexico, demonstrates our expertise. Using ESRI ArcGIS technology, we manage wide-ranging asset networks in real-time on AWS, offering a cost-effective solution for managing large databases.

This system, accessible worldwide through a Web Application, sets a benchmark for efficient asset management across different sectors. Our methods significantly improve project and operational efficiency, particularly in the Architecture, Engineering, and Construction (AEC) industry, providing a practical model for managing construction assets with precision.

With our remote teams spread across Europe and America, Struverse is leading the way in digital transformation, ensuring scalable, cost-effective cloud infrastructure solutions for our clients.

E-Bikes Everywhere: Optimising Urban Transportation and Advertising through ML

E-Bikes Everywhere optimised urban transportation and advertising data usage, increasing Telefónica’s revenue through strategic optimisation of advertising space integrated with an e-bike sharing service.

The Challenge

Maintaining urban e-bike systems is costly and service fees alone cannot cover expenses. Inconsistent subsidies further challenge financial sustainability.

The Solution

We combined e-bike sharing with smart urban advertising. Telefónica provided the technology, ensuring seamless operation. Data-driven advertising was integrated to create a sustainable business model.

Leveraging Machine Learning

Machine learning was central to our solution. We analysed extensive e-bike data using advanced algorithms for optimal decision-making in transportation and advertising.

Key Machine Learning Models

  1. HDBSCAN Clustering: Identified high-traffic areas, enabling strategic placement of advertising posts.
  2. XGBoost Regression: Predicted usage patterns and ad impressions, optimising ad placements based on time, demographics, and location.

Key Outcomes

  • Optimized Post Allocation: Strategically placed advertising posts in high-traffic areas.
  • Targeted Advertising: Scheduled ads based on peak usage times and user demographics.
  • Enhanced Revenue: Applied premium rates for high-impact locations, generating significant additional revenue.

Project Results

Our project led to improved post allocation, optimised advertising strategies, and paved the way for higher revenue. This integration of smart mobility with data-driven advertising ensured the long-term viability of the e-bike sharing service.