FM Fernando Muerza Data Scientist
Contact
Data Scientist — PropTech · Real Estate · Fintech

Fernando
Muerza

ML models for pricing, valuation and multi-channel attribution — shipped all the way to production.
Real pipelines (REST APIs, Docker, scheduled retraining) across real estate, financial markets and performance marketing. Measured, never guessed.
Available 100% remote from CDMX · CT/ET overlap
View projects →
Contact me
R² · valuation
0.904
Cost / lead
−70.76%
Valuation · was 4 h
39s
Valuation report Sample
House · Lomas de Angelópolis, Puebla
Estimated value
$8,043,200
80% INTERVAL±10%
$7.24M$8.85M
R²
0.904
Retraining
7 days
Inference
39 s
Model
LightGBM
History+18% / 12m
In production · scikit-learn · Django / Docker
R² · real-estate valuation
0.904
Cost per lead · attribution
−70.76%
Valuation in production
39s
before · 4 h
Scheduled retraining
7days
§ 01 — About
Retrato de Fernando Muerza (placeholder)
Fernando MuerzaCDMX · MX
SpanishNative
EnglishB1 → B2, improving

Data Scientist with end-to-end experience in pricing, valuation and attribution.

I build ML models for pricing, valuation and multi-channel attribution, and I take the pipelines to production: REST APIs, Docker and scheduled retraining, in domains where the data and the economics behind it both matter.
Models running in production with R² = 0.904 in real-estate valuation and a −70.76% cut in cost per lead through multi-channel attribution. Formal training in equity valuation (Damodaran · NYU Stern) and real-estate valuation (IBERO Puebla).
Domain
Real Estate
valuation & classification
Domain
Fintech
markets & risk
Domain
Performance
multi-channel attribution
§ 02 — Skills

End-to-end solutions, delivered to production.

01
Predictive modeling & ML
—Data cleaning, EDA and validation
—Feature engineering
—SQL: joins, aggregations and window functions
02
Modeling & evaluation
—Classification and regression
—Metrics: AUC, F1, RMSE, sMAPE
—Validation and leakage control
03
Production & automation
—Model-serving APIs (Django)
—Docker and VPS deployment
—Automation: webhooks, APIs, pagination
PythonPython PandasPandas NumPyNumPy scikit-learnscikit-learn TensorFlowTensorFlow PyTorchPyTorch KerasKeras DjangoDjango DockerDocker PostgreSQLPostgreSQL GitGit JupyterJupyter PythonPython PandasPandas NumPyNumPy scikit-learnscikit-learn TensorFlowTensorFlow PyTorchPyTorch KerasKeras DjangoDjango DockerDocker PostgreSQLPostgreSQL GitGit JupyterJupyter
§ 03 — Projects

Featured projects

github.com/muerza ↗
In productionInmuebles Anzuz · 2024 — present

Real-estate valuation

End-to-end valuation and classification models: multi-source data preparation, feature engineering with scikit-learn, data-quality controls and scheduled retraining. Deployed as a Django API on Docker/VPS, with confidence intervals for robust decisions under uncertainty.
scikit-learnLightGBMDjangoDockerVPS
Try the ML Valuator →
R²0.904
Inference39 s
Before4 h
Retraining7 days
Oily Giant↗

Oil well selection

Regions with the best expected return, factoring in uncertainty and risk: bootstrapping, confidence intervals and profit simulation.

RegressionBootstrapping
Zyfra↗

Gold recovery

Model to predict gold recovery and optimize production. Focused on cleaning, feature consistency and process metrics.

Feature eng.sMAPE
Beta Bank↗

Churn prediction

Identify customers with a high probability of leaving so retention can focus on the highest-risk segments. Class balancing and evaluation.

ClassificationF1 · AUC-ROC
§ 04 — Live demo

ML Valuator — Lomas de Angelópolis

Price estimated with LightGBM trained on real market data from Puebla. Adjust the parameters and get a valuation with its confidence interval.
LightGBM · live
Property parameters
Operation
Estimated price House · Lomas 2
$8,043,200
CONFIDENCE INTERVAL · 80%±10%
$7,239,000estimate$8,848,000
Top factors
Built m² $5.7M · 65%
Land m² $1.4M · 16%
Zone (Lomas 2) $731k · 8%
Bedrooms and bathrooms $528k · 6%
Base / location $385k · 4%
LightGBM model trained on Puebla market data. Illustrative estimate — not an official appraisal.
§ 05 — Track record

Experience & education

01
Nov 2023 — present Experience

Data Scientist

— Inmuebles Anzuz

Real-estate valuation ML models, taken end to end into production:

R² 0.904
Valuation model with LightGBM and scikit-learn; feature encoding of numeric and categorical variables from multiple sources
−99.7%
Valuation time (4 h → 39 s), exposing the model as a REST API in Django on Docker / VPS
7 days
ETL pipeline with scheduled retraining to hold performance as the market shifts
Data
Data-quality controls and percentile outlier filters to stabilize training
02
2025 — ongoing Education

System Design Mastery

— ByteMonk Academy

System design focused on scalable architectures (load balancing, consistency) and hands-on case practice. Applied to: model APIs and services that are more scalable, reliable and production-ready.

03
2025 — 2026 Education

Data Scientist Boot Camp

— TripleTen

Hands-on, solution-oriented training: from fundamentals (Python / Pandas) through machine learning and neural networks, with reproducible deliverables and portfolio evidence.

04
2025 Education

Make Advanced

— Make Academy

Robust automation: advanced webhooks, API calls with HTTP modules, pagination and data stores. Applied to: orchestrating ETL/MLOps integrations (ingestion, retraining, validation and alerting).

05
Feb 2021 — Oct 2023 Experience

Commercial Operations Analyst

— Inmuebles Anzuz

Marketing analytics and funnel automation on campaign and CRM data:

−70.76%
Cost per lead on Meta Ads with server-side tracking (CAPI · Stape · GTM): $182.62 → $53.40 MXN
+72.32%
Funnel traceability with URL-parameter attribution in Zoho CRM
432×
Sales response time (36 h → 5 min) with lead capture and routing through APIs in n8n
Make
Contract generation with webhooks over CRM data, cutting errors and rework
06
2023 Education

Real-estate management

— IBERO Puebla

Formal training in real-estate management and appraisal — the domain foundation behind the pricing and valuation models.

07
2018 — 2022 Education

BBA, Business Administration

— UPAEP

Strategic and diagnostic foundation, with quantitative coursework (statistics, business mathematics). Applied to: turning technical findings into actionable decisions and communicating impact to non-technical stakeholders.

08
Aug 2018 — Jan 2021 Experience

Operations & Data Analyst

— Baoba

Automation of reporting and commercial processes at a panel and veneer manufacturer:

−5 h/wk
KPI reports and dashboards automated in Excel — (~260 h/year) of manual work removed
−85%
Time per quote (10 → 1.5 min) with a rule-based quoting system
−97%
Weekly process errors (35 → 1) with the same system
09
2019 — 2020 Education

Valuation & Corporate Finance

— Aswath Damodaran · NYU Stern

Valuation and corporate finance with a practical focus. Applied to: translating business and finance variables into defensible features and assumptions in proptech and fintech models.

§ 06 — Blog

Articles & technical notes

How I build models that actually reach production — valuation, attribution and MLOps, with the numbers behind them.
All articles ↗
Portada artículo 1 (placeholder)
ML valuation Feb 2026

How I took a real-estate valuation model to production (R² 0.904)

From EDA to deploy: feature engineering with LightGBM, data-quality controls and a Django API that answers in 39 s.

8 min read Read →
Portada artículo 2 (placeholder)
Attribution Jan 2026

Server-side tracking: how I cut cost per lead by 70.76%

Meta CAPI, Stape and GTM to recover signal, close the funnel and attribute every peso to the right channel.

6 min read Read →
Portada artículo 3 (placeholder)
MLOps · Production Dec 2025

From notebook to API: shipping ML with Django and Docker

Scheduled retraining, versioning and an ETL pipeline that holds performance when the market moves.

7 min read Read →
§ 07 — Contact

Let's work
together

Have an opening, or a pricing, valuation or attribution project in mind? Send me a message and I’ll get back to you.
Available 100% remoteCDMX · CT/ET
Leave your details