Calazans Macchiutti

About Me

Welcome to my website! I'm Calazans Macchiutti, a Data Scientist with a Ph.D. in Physics (CBPF) and a strong background in statistical modeling, scientific reasoning, and applied machine learning.

Today, I work as a Data Scientist at ESPM, where I build data solutions that support strategic academic decision-making, including predictive analytics, KPI development, automation pipelines, and dashboards. I enjoy turning complex and messy data into clear insights, reliable metrics, and scalable products that improve real-world processes.

My academic training gave me a rigorous foundation in problem-solving, experimental design, and quantitative analysis. Over time, I transitioned that expertise into industry-focused work, applying machine learning to time series, anomaly detection, and performance forecasting — always aiming for practical impact, clarity, and measurable results.

Areas of Focus

Machine Learning & Predictive Modeling: classification, forecasting, anomaly detection
Time Series Analytics: pattern recognition, monitoring, efficiency indicators
Applied Data Science: dashboards, KPI frameworks, data quality metrics
Automation & Data Pipelines: scalable workflows for analytics and reporting
AI for Decision Support: insights that improve processes and operations

Professional Experience

Data Scientist — ESPM (2024–Present)
Senior Data Scientist — BINAHKI (2023–2024)
Ph.D. Researcher — CBPF (2020–2024)

I'm especially motivated by projects where data can drive better decisions, optimize resources, and improve outcomes. If you're looking for a Data Scientist who combines technical depth, strong analytical thinking, and a practical product-driven mindset, feel free to reach out.

Academic Profile

Research in Condensed Matter Physics and Materials Science

Research Focus

During my doctoral program, I focused my studies on the physical properties of transition metal oxides, with a special emphasis on the investigation of double perovskite-type structures and their impact on the "exchange bias" phenomenon.

My research covers a variety of techniques:

Magnetic measurements
Electrical and thermal transport studies
X-ray diffraction
Magnetoresistance analysis
Investigation of strong electronic correlation phenomena

Materials Synthesis Experience

Extensive experience in materials synthesis through various methods:

Sol-gel synthesis
Co-precipitation methods
Solid-state synthesis
Floating zone techniques

All syntheses included both polycrystals and single crystals of ternary and quaternary rare earth oxides, as well as binary single crystals such as V₂O₅.

Characterization Techniques

X-ray photoelectron spectroscopy (XPS)
Raman spectroscopy
Atomic force microscopy (AFM)

Early Research

Musical Acoustics and Environmental Acoustics
Applications of electromagnetic waves in magnetic resonance
Analysis of sound waves in music

View all publications →

Data Science

Professional Summary

My journey has been shaped by the development and application of statistical models, with a strong focus on identifying patterns, understanding trends, and generating actionable insights.

I developed a strong foundation in scientific problem-solving, quantitative modeling, and rigorous analytical reasoning through end-to-end research projects. This experience includes hypothesis formulation, experimental planning, data acquisition, and the interpretation of complex multivariate phenomena. With this background, I present below a detailed overview of my professional trajectory from a technical perspective.

Technical Skills

Programming & Data Manipulation

Python (Pandas, Polars, NumPy)
SQL for querying, transformation, and data management
Dask and PySpark for large-scale processing

Data Visualization & Statistical Analysis

Matplotlib, Seaborn, Plotly
SciPy and Statsmodels for statistical modeling and inference

Machine Learning & AI

TensorFlow, Keras, Scikit-learn, XGBoost
Prophet and Darts for forecasting and time series modeling

Cloud & Ops

Docker for containerization and portability
AWS and Azure for scalable cloud architectures
GitHub for version control and collaboration
Hugging Face for model deployment and sharing

Computer Vision & Media Processing

OpenCV for image and video processing
MoviePy and FFmpeg for video automation
Pillow for image manipulation

Generative AI

LLMs (Claude, ChatGPT, Gemini) - Advanced proficiency

Professional Experience

ESPM (Superior School of Advertising and Marketing)

Data Scientist | Aug 2024 – Present

At ESPM, I work on restructuring the data lifecycle across extraction, loading, and transformation workflows, while also designing and maintaining a set of academic quality indicators that support strategic decision-making and pedagogical evaluation.

A major part of my role involves developing and structuring KPIs related to student attraction, retention, progression, and academic performance over time. These indicators allow us to monitor academic outcomes across different admission channels and understand how student performance evolves throughout the program.

In parallel, I help develop analytical products that support the segmentation and classification of newly admitted students, enabling early identification of those who may require academic reinforcement based on previously defined metrics and performance indicators.

Beyond the technical implementation, I actively contribute to the conceptual design of the metrics and frameworks used to map the full academic ecosystem. This includes translating educational goals into measurable indicators, validating assumptions with data, and communicating results to stakeholders.

I also work on complementary solutions such as dashboards that integrate machine learning outputs with academic metadata, as well as automation tools for academic operations. One example is the development of an internal exam-generation platform, which improves efficiency, reduces operational cost, and strengthens the data foundation required to support the KPIs built for institutional monitoring.

Predictive Analytics: KPI dashboards for approval rates, retention, and academic completion
Applied Research: ML/AI approaches applied to interdisciplinary academic datasets
Data Products: Analytics solutions supporting academic management and learning strategies
Process Optimization: Resource allocation analysis and operational efficiency improvements

Tech: Python, Power BI, SQL, PySpark, MLflow, Azure

BINAHKI

Senior Data Scientist | Nov 2023 – Aug 2024

At BINAHKI, I worked on smart monitoring products for multinational clients such as ZF Friedrichshafen, using IoT sensor data to monitor industrial machines and optimize production processes.

The main project involved monitoring industrial furnaces used in steel production through electrical voltage signals. The sensor data was stored in a cloud-based SQL environment integrated with AWS S3, and the pipeline included data ingestion, processing, and model-based detection of operational cycles.

Using Python and TensorFlow, I trained time series models to learn normal behavior patterns and identify key events such as the start and end of each production batch. Based on this cycle-level detection, I built statistical energy-consumption parameters that enabled forecasting of monthly usage and measurement of production efficiency.

In addition to furnace monitoring, similar IoT solutions were deployed to other industrial machines with the same objective: anomaly detection for predictive maintenance. These models supported early identification of abnormal behavior in equipment involving pumps, torque systems, and mechanical load.

Beyond product development, I also contributed to the design and architecture of data science solutions for public innovation calls. These initiatives resulted in successful proposals, including a project for a sanitation company focused on correcting missing and anomalous records using multivariate time series methods and statistical models such as ARIMAX.

Tech: Python, SQL, AWS S3, SageMaker

CBPF (Brazilian Center for Research in Physics)

Scientist | Nov 2017 – Jan 2024

My Master's research focused on combining systematic investigation with advanced laboratory methodology and quantitative interpretation of experimental results. This experience strengthened my ability to convert complex measurements into reliable scientific conclusions.

During my PhD, I conducted a systematic optimization study of physical properties under controlled experimental conditions. I compared the same material across multiple processing configurations and extracted insights from structural, microstructural, electronic, and magnetic datasets. This work required high analytical rigor, reproducibility, and careful interpretation of nonlinear behavior, reinforcing my ability to investigate complex systems and identify causal relationships in data.

This research path strengthened key Data Science capabilities such as experimental design thinking, statistical reasoning, pattern recognition, critical validation, and technical communication. Most importantly, it reinforced the ability to structure findings into clear narratives supported by evidence and consistent methodology.

Publications

2025

Enhanced oxygen mobility in NiAg alloy catalysts for methane dry reforming

ARG Caranton, AVP Lino, C Macchiutti, NRC Huaman, E Annese

Catalysis Today, 455, 115316 (2025)

DOI

2024

Optimization of the exchange bias effect in La₁.₅Sr₀.₅CoMnO₆

Calazans Macchiutti - Ph.D. Thesis, CBPF (2024)

PDF

Tuning the spontaneous exchange bias effect in La₁.₅Sr₀.₅CoMnO₆

JR Jesus, FB Carneiro, L Bufaiçal, RA Klein, Q Zhang, C Macchiutti

Physical Review Materials, 8(4), 044408 (2024)

DOI

2023

3d and 5d electronic structures in Ba- and Ca-doped double perovskites

JRL Mardegan, LSI Veiga, T Pohlmann, et al., C Macchiutti

Physical Review B, 107(21), 214427 (2023)

DOI

2022

Structural, electronic and magnetic properties of La₁.₅Ca₀.₅(Co₀.₅Fe₀.₅)IrO₆

L Bufaiçal, MAV Heringer, JR Jesus, A Caytuero, C Macchiutti, EM Bittar

J. Magn. Magn. Mater., 556, 169408 (2022)

DOI

2021

Master's Thesis: Synthesis and characterization of single crystals

Calazans Macchiutti - CBPF (2021)

PDF

Absence of zero-field-cooled exchange bias effect in single crystalline compounds

C Macchiutti, JR Jesus, FB Carneiro, L Bufaiçal, M Ciomaga Hatnean

Physical Review Materials, 5(9), 094402 (2021)

DOI

2020

Tuning the spontaneous exchange bias effect with Ba to Sr partial substitution

M Boldrin, AG Silva, LT Coutrim, JR Jesus, C Macchiutti, EM Bittar

Applied Physics Letters, 117(21), 212402 (2020)

DOI

Unveiling charge density wave quantum phase transitions by x-ray diffraction

FB Carneiro, LSI Veiga, JRL Mardegan, R Khan, C Macchiutti, A López

Physical Review B, 101(19), 195135 (2020)

DOI

2019

Zero-field-cooled exchange bias effect in phase-segregated La₂₋ₓAₓCoMnO₆₋δ

LT Coutrim, D Rigitano, C Macchiutti, TJA Mori, R Lora-Serrano

Physical Review B, 100(5), 054428 (2019)

DOI

2017

Física e Música (Physics and Music)

FN Grillo, HE Perez, C Macchiutti - Book, MNPEF (2017)

Co-author of Chapter 3 on physics and music.

PDF

ADS Library | ORCID: 0000-0002-8571-8876

Projects

Fraud Detection (KYC/KYT)

ML-based fraud detection comparing supervised and unsupervised approaches.

Python XGBoost TensorFlow Scikit-learn

Logistic Data Assessment

Analytics suite for tracking delays, seasonality, and predictive risk scoring.

Python Pandas LightGBM FastAPI

Streamlit Applications

Interactive web applications for data visualization and analysis.

Python Streamlit Plotly

Voltage Time Series LSTM

LSTM neural network for voltage prediction and anomaly detection.

Python TensorFlow LSTM

Magnetism Techniques Thesis

Research code and analysis for magnetism techniques thesis work.

Research Data Analysis

GitHub

View all repositories on GitHub

Logistic Data Assessment

Exploratory and predictive analytics for operational efficiency in logistic networks

Screenshots

Departure Delays

Seasonality

Model Insights

Project Overview

This project consolidates exploratory analysis, KPI monitoring, and predictive modeling for a logistic operation handling thousands of daily deliveries. The objective is to surface actionable insights for dispatch planning, identify systemic bottlenecks, and forecast risk factors that affect service-level agreements.

Key Questions Answered

What routes, hubs, and shifts are the main contributors to departure delays?
How do seasonal patterns and workload peaks affect fleet punctuality?
Which operational variables most influence delay risk according to the predictive models?

Analytical Highlights

Interactive dashboards covering delay distribution, seasonal effects, and operational KPIs
Machine learning pipeline (gradient boosting and logistic regression) for delay risk scoring
Explainability layer with feature importance, SHAP interpretation, and scenario simulation
Automated data quality checks and anomaly alerts for incoming logistic batches

Workflow

Data ingestion from transactional systems and IoT telemetry with validation routines
Feature engineering combining route metadata, fleet schedules, weather, and customer SLAs
Model training and cross-validation with monitoring for drift and performance decay
Packaging of results into dashboards and API endpoints for operational teams

Technologies

Python Pandas Polars Scikit-learn LightGBM Plotly FastAPI

Results & Impact

The combined analytical assets helped reduce average departure delays by 18% in pilot operations, while the predictive service highlighted upcoming high-risk routes with over 80% precision. Operational teams now rely on the dashboards to reallocate resources earlier and plan contingencies for peak seasons.

View on GitHub ← Back to Projects