Market Landscape & Segmentation

Construction of a system for enriching company client data, taking information from public files (BORME, BOE, Commercial Registry), open APIs and web scrapping.

Data analysis and processing for detection of connections, target audiences, etc. and integration into a business intelligence tool.

Activities:

  • Ingestion and transformation of data from internal systems.
  • Construction of external data collection robots (Mercantil Registry, Google Places API, webs, etc).
  • Implementation of cleaning, deduplication and data quality processes.
  • Descriptive data analysis based on graphs and machine learning algorithms.
  • Integration of results with corporate information tools.

Technologies:

Amazon Web Services (EMR, Redshift, EC2), Apache Spark, Neo4j, R, Python.

Type of project and dates:

  • Turnkey project
  • Start: Q4 2015.
  • End: Q2 2017.