Malt welcome

¡Bienvenido al perfil Malt de Belén !

Malt te da acceso a los mejores talentos freelance para tus proyectos. Ponte en contacto con Belén para hablar de tus necesidades o busca otros perfiles en Malt.

Belén Navarro

Data, Marketing & Sales - Retail, Luxe & Health
Supermalter
  • Tarifa aproximada
    340 € /día
  • Experiencia8-15 años
  • Tasa de respuesta100%
  • Tiempo de respuesta1h
El proyecto se dará por comenzado una vez hayas aceptado el presupuesto de Belén.
Localización y desplazamiento
Localización
Madrid, España
Puede trabajar en tus oficinas en
  • Madrid y alrededores (hasta 50 kms)
Verificaciones

Código de conducta freelance firmado

Consultar el código
E-mail verificado
Idiomas
Categorías
Compartir su perfil
Estos perfiles también corresponden a tu búsqueda
Agatha FrydrychAF

Agatha Frydrych

Backend Java Software Engineer

Baptiste DuhenBD

Baptiste Duhen

Fullstack developer

Amed HamouAH

Amed Hamou

Senior Lead Developer

Audrey ChampionAC

Audrey Champion

Web developer

Conjunto de habilidades profesionales (35)
Sector de especialización
Belén en pocas palabras

With over 10 years of consultancy experience, I excel in leading transformative initiatives and aligning business objectives with IT strategies to drive growth. My expertise in data analytics, especially in cloud services, social media, and business intelligence, positions me to spearhead strategic initiatives as a Network Strategy Manager. I ensure seamless integration of technologies and business goals for
sustained success. Selected for AI for Women - Google
Experiencia
  • MAPFRE (Desarrollo de negocio Digital)
    Data Eng (Business, Data + AI
    BANCA & SEGUROS
    septiembre de 2024 - Hoy (3 meses)
    Madrid, España
    - AWS - GCP data migration
    - Adobe CDP
    - GCP BigQuery

    -Data migration: I planned and executed the migration of large volumes of data, ensuring the integrity and quality of information throughout the process.
    -Database construction: I designed and developed highly scalable data tables and cubes in Google Cloud, optimising the structure for advanced analytics and agile queries.
    -Interactive dashboard creation: I migrated and enhanced existing Power BI dashboards to Google Cloud, incorporating new visualisations and functionality to facilitate data exploration and actionable insights generation.
    -Data exploration and machine learning model development: I performed a deep exploratory analysis of the data, identifying relevant patterns and trends. From these insights, I developed machine learning models to predict [mention specific use cases, e.g. customer churn, fraud detection, etc.].
    -Implementation of data products: I collaborated closely with business teams to transform the insights obtained into tangible data products, which enabled process optimisation and improved decision making.
  • Google Campus
    AI Researcher
    abril de 2024 - julio de 2024 (4 meses)
    AI Researcher - Google Campus
    Developing an AI-Driven Antibiotic Sensitivity Prediction Model to determine bacterial susceptibility to
    antibiotics based on various data sources including metabolomic profiles (potentially derived from
    mass spectrometry).
    Employed machine learning techniques like supervised learning (logistic regression, decision trees)
    and deep learning (CNNs, RNNs) to analyze biological data and predict antibiotic resistance.
    Utilized MLOps principles to streamline the model development process, ensuring efficient
    deployment into production environments.
    Key data:
    • Genome
    • Proteome
    • Phenotype
    • Susceptibility tests
    • Clinical information
    AI Techniques
    • Machine Learning:
    o Supervised learning: Algorithms such as logistic regression, decision trees, or
    artificial neural networks are used to predict the sensitivity or resistance of a
    bacterium to an antibiotic based on its characteristics and the properties of the
    antibiotic.
    o Unsupervised learning: Techniques such as clustering are used to identify
    groups of bacteria with similar resistance patterns.
    • Deep Neural Networks:
    o Convolutional neural networks (CNN): Used to analyze electron microscopy
    images and detect morphological features associated with resistance.
    o Recurrent neural networks (RNN): Applied to analyze genomic sequences
    and predict the presence of resistance genes.
    • Reinforcement Learning:
    o Models can be developed that learn to select the best antibiotic treatment
    based on the patient's characteristics, the bacterium, and the results obtained.
    Google cloud AI MLOps Data science Data integration
  • Abbott Laboratories (UK)
    Business Intelligence @ Cardiac Rhythm Management
    INDUSTRIA FARMACÉUTICA
    septiembre de 2023 - marzo de 2024 (7 meses)
    •Define the Sales Strategy and KPIs from a deep data analysis (Sales Revenue, Mkt Share, Service& Support)
    • Design and day to day of different BI reports: PowerBI & Looker, SAP BO
    • Business unit development & sales management, marketing and education activities supporting the
    regional distributor.

    SAP Microsoft Power BI Adobe CDP
Recomendaciones externas
Formación
  • Master of Business
    ESCP EUROPE
    2015
    MBA, Master of Business Administration
  • Master of Data Science
    Rey Juan Carlos University
    2014
    Master in Data Analysis
  • Bachelor of Business Administration
    Universidad Complutense
    2012
    Bachelor in Journalism & Business Administration
Certificados
  • SalesForce
    Salesforce
    2022