• Contact Info :
  • Torres Vedras, Portugal
  • valterjpcaldeira@gmail.com
  • Follow me :

I'M Valter Caldeira

A

I have been working as Lead Data Scientist in Healthcare companies to find opportunities to get insights from their business by using Machine Learning, Real World Evidence, Realtime AI Algorithms, NLP, Speech Processing, whathever make sense! I have experience in creating and developing AI / ML solutions, providing technical solutions that ensure application performance, lifecycle agility, maintainability and governance.

/
/
About Me

About Me

/

AI/ML Lead Data Scientist

  • Age : 30

  • Birthday : 4 April 1992

  • Email : valterjpcaldeira@gmail.com

  • City : Torres Vedras, Portugal

  • Hobby : Boardgames

0

Projects as Team Leader

0

Projects

0

Trained People

0

Number of Coffees

My Resume

My Resume

Experience

Lead Data Scientist @Beats Medical

2021 - Current

Digital Therapy Development:

  • RWE (Real World Evidence) Get Real World Data - Create RWD based on all the data extracted by the app
  • TUG (Time Up and GO) - Enable AI/ML to be able to detect duration of TUG on mobile app using only the acceloremeter
  • System and Method Configured for analysing acoustic parameters of speech to detect, diagnose, predict and/or monitor progression of a condition, disorder or disease - Patent Pending.

I have also developed some Power BI dashboards to help the mobile team debug some of the exercises easily

Lead Data Scientist @Tenthpin

2019 - 2021

Several projects in healthcare:

  • RWE (Real World Evidence) Platform in Life Science - Create RWE new architecture for supporting all Data Science teams.
  • RPA with AI/ML Strategy - Enable AI/ML in Automated Processes using UIPtah / Automation Anywhere
  • Article summarization - Team Leader and Responsible to brainstoming with the client and Scientist that helped to understand the problem.
  • Invoice Classification – Developer and Responsible to present results to the Client.

I have also developed some Power BI dashboards and also reports in SAP ByDesign Reports

Data Scientist @Novabase GTE

2017 - 2019

Several projects in government:

  • Smart Search Engine – Team Leader, Responsible for Communication with Client.
  • Custom Tariff Number Classifier – Team Leader, Responsible for Communication with Client.
  • Census Accelerator – Team Leader, Developer and Responsible for teaching Python, Data Science and ML to junior members.
  • Business Insights - Team Leader, Responsible to present the solutuion to the Client and also Developer
  • English/Portuguese NLP Tool – Team Leader, Developer and Responsible for a inside tool we have created to work with some NLP models.
  • CAE Classifier – Team Leader, Developer

I have also worked in some workshops to teach the basics about AI to all employees in the company

Java Full-Stack Developer @Novabase Portals

2014 - 2017

Several projects in government (Java, PostgreSQL, OracleDB, SpringMVC, Liferay, REST, SOAP, HTML, CSS, Javascript):

  • SINERGIC - Sistema Nacional de Informação Cadastral – Team Leader, Full-Stack Java Developer.
  • DNS.PT – Team Leader, Full-Stack Java Developer.
  • AT Mozambique – Team Leader, Full-Stack Java Developer.
  • E360 - Education Portal – Full-Stack Java Developer.
  • CTT Indicators - FrontEnd Developer

My Skills

Python
95%
NLP / Speech Processing
85%
Machine Learning / AI Algorithms
80%
Realtime Processing
75%
SQL / NoSQL
90%
Power BI
80%
Java
60%
Azure
60%
Key Projects

Key Projects

/
Article Summarization

Article summarization and insights gathering for Research Company: Python (Keras, TensorFlow, Sklearn, Gensim, Nltk, etc.).

/
Invoice Error Classification

Deployment of Invoice Classification for a drug company: Python (Pandas, Numpy, Sklearn, Tensorflow).

/
Custom Tariff Q&A

Create a model to answer to user questions based in the current Q&A: Python (Pandas, BERT, Numpy, NLTK)

/
Business Website Data Insights

Web Scraping project to gather insights about UK companies using NLP: Python (Selenium, MongoDB Atlas, Flask, Nginx, Sklearn, Gensim, Nltk.).

/
CAE Classifier

Classify (CAE) activity code based on a description sentence (Portuguese Language): Python (Pandas, Numpy, Sklearn, Gensim).

/
Census Quality Controller

Using NLP algorithms to help ensure Quality control in Mozambique Census: Python (Pandas, Numpy, Levenshtein distance).

Personal Projects

Personal Projects

/
Dice Geek
/
Product Detection Demo
/
Recount
/
Bits... Please
/
MusicV
/
Telma & João
Certifications and Trainning

Certifications and Trainning

Blog Articles

Blog Articles

/
  • May, 2022
Redefining Digital Biomarkers

Biomarkers have been crucial in transforming clinical practice in several therapy areas by enabling precision medicine. With the increase in use and popularity of digital devices and health related mobile apps, we are witnessing the emergence of digital biomarkers.

/
  • Jun, 2021
Enabling RWE Use Cases through Data Analytics

The introduction of advanced analytics in RWE has made real-world data a more powerful resource for pharma companies

/
  • Aug, 2020
Digital Transfoprmation through RPA

One step forward in the digital revolution: RPA & Analytics

/
  • April, 2020
ERP & Data Science

Many companies have complex ERP’s that capture and store most of their business data in one place

/
  • March, 2019
Why nobody plays board games?

Board games are pretty cool!