Skip to content

EyeNova

Crosses the commercial trail with the actual sale and turns two loose lists into a customer profile.

Vertical: Real estate and banking Functional or partial

What it is for

Answer the question almost no real estate operation has solved: of all the interest recorded, what ended in a sale, who was behind it, and what the people who did buy have in common.

What it does

Ingests commercial interest records and sales records, cleans them, resolves which records belong to the same person even when the data does not match literally, places them by province and region, and builds a customer profile with search, advanced filtering and profile-to-profile comparison. It runs entirely on the client’s own infrastructure.

Sector

Real estate and bank-owned assets: portfolio marketing, servicers and sales teams.

What it improves

Reconciling interest against sales is done today by hand on spreadsheets, with duplicates and no stable notion of identity. Here it is a repeatable process, and comparing customers stops being an impression and becomes a query.

Target client

Real estate and bank portfolio marketers, and in-house sales teams with enough volume that manual matching is no longer viable.

Status and maturity

Functional with declared debt: ingestion, identity resolution, the customer profile and the analytics are built and operational. The artificial intelligence modules are designed as pluggable pieces and are left for later phases.

Differentiator

Identity resolution tolerant to typos and name variants is the hard part, and it is solved. And everything works with no data egress: the system is installed where the information lives, which in bank portfolios is not negotiable.

Commercial fit

Per-installation licence with commissioning services and source adaptation. It fits as the natural complement to Nemea over the same portfolio.

Architecture

Layered architecture

A short data pipeline with a query on top. All the value sits in the middle stretch: deciding which records are the same person when the data does not match literally. The system is installed where the information lives and never takes it out.

  1. 01

    Ingestion and cleaning

    Intake of commercial interest records and sales records, with format normalisation and sanitation of the fields that later carry the match.

  2. 02

    Identity resolution

    Decides which records belong to the same person despite typos, abbreviations, surname order and spelling variants. It is the hard stretch and the one that gives the rest its meaning.

  3. 03

    Territorial normalisation

    Assignment of every record to its province and region, so that reading by territory is comparable across sources.

  4. 04

    Customer profile and querying

    Construction of the unified profile, with search, advanced filtering and profile-to-profile comparison.

  5. 05

    Analytics

    Aggregate reading over the resolved match: how much of the recorded interest ended in a sale, and what the buyers have in common.

  6. 06

    Intelligence modules

    A planned, isolated space for machine learning pieces, designed as pluggable so the product does not depend on them.

Inventory

Status per component

A real inventory of the asset’s components with their declared status. We publish capability, never code or internal figures.

Built and testedFunctional with declared debtDesigned, not implementedWired; depends on a third party

  • Ingestion and cleaning

    Built and tested

    Built and operational over the client’s real sources.

  • Identity resolution

    Built and tested

    Tolerant to typos and name variants. It is the asset’s differentiator.

  • Territorial normalisation

    Built and tested

    Province and region assigned consistently.

  • Profile, search and comparison

    Built and tested

    The main surface of use, with advanced filtering and profile-to-profile comparison.

  • Aggregate analytics

    Built and tested

    Conversion and profile reading over the resolved match.

  • Execution inside the client perimeter

    Built and tested

    Self-contained deployment: data never leaves the infrastructure where it is installed, which in bank portfolios is not negotiable.

  • Machine learning modules

    Designed, not implemented

    Designed as pluggable pieces and not implemented. Declared so nobody mistakes a planned slot for an existing capability.

  • Semantic similarity search

    Designed, not implemented

    Anticipated in the data model, not implemented.

This profile describes capabilities and status, not implementation. Code, architecture documentation and internal figures are shared under a confidentiality agreement during due diligence.

Platforms

Moeris

Cybersecurity

Prepares an organisation for the day today’s cryptography stops protecting its data.

Solid base Read the profile

Hecate

Cybersecurity

Protects dozens of client companies from a single console, without mixing their data.

Solid base Read the profile

Nemea

Real estate and banking

Turns bank debt and real-estate portfolios into exploitable investment intelligence.

Solid base Read the profile

Infinity

Real estate and banking

Publishes new-build real-estate developments automatically, with its own viewer and the client’s brand.

Solid base Read the profile
Describe a case See all platforms