Nicolas Keller
Verified Expert in Engineering
Data Scientist and Developer
With a strong mathematical background (a master's degree in mathematics), 尼古拉斯是一位充满激情的数据科学家,他可以为机器学习知识的理想组合做出贡献, practical programming skills, and a problem solving and analytical mindset to a project. 他有将业务问题转化为数据驱动解决方案的经验,最近在这家全球保险公司担任数据科学家, Allianz.
Portfolio
Experience
Availability
Preferred Environment
Jupyter Notebook, RStudio, Git, Linux
The most amazing...
...我编写的是一个R程序包,可以根据个人特征预测人寿保险索赔. It is a novel approach going beyond the status quo.
Work Experience
Data Science Lead
Pfizer
- 领导临床试验领域的数据科学和数据工程项目的发展.
- Set up a cloud infrastructure for model training, deployment, and application prototyping, which increased the impact and visibility of our team within the organization.
- 设计和管理Neo4j图形数据库,以集中组织数据集,并利用图形算法来回答复杂的业务问题.
- Developed an interface to the graph database, allowing non-technical users to ask questions in natural language. 我们训练了一个深度学习模型将英语翻译成Cypher(图查询语言).
- 创建了一个优化算法,以选择最佳的临床试验地点,并监督试验的推出和整合到业务运营中.
Data Engineer
IPPMed GmbH
- Supported the external adjudication process of two medical studies.
- 使用Python自动完成合并、填充和发送大量PDF表单的过程.
- 通过自动Excel表格跟踪与裁判的数据交换,并提供仪表板来创建进度报告.
- Used Selenium to automate downloading and gathering PDF files from a website, which would have been weeks of manual work.
Data Scientist
Focus Sensors Limited
- 研究了传感器数据异常检测算法的广泛代码库的实现和数学概念.
- Changed the core architecture from static data files to streaming data using Kafka.
- 在处理时间和输出完整性方面测试并优化了新架构.
Data Scientist
Moneyhub
- 使用AWS SageMaker和Lambda基础设施实现并生产了一种个性化的机器学习算法,对交易数据进行分类.
- 检测客户行为的趋势,并创建频繁的报告来呈现结果, which have been published regularly on the company's website.
- 完成各种数据分析和poc,以响应业务请求,使用SQL和Python作为后端,使用Jupyter Notebooks和Plotly来呈现结果.
Data Scientist
TradeDepot
- 分析小额贷款数据,找出影响还款行为的相关特征.
- 实现并测试了一个Python模块,该模块返回信用风险评分以及详细解释.
- 将该模块部署在AWS SageMaker和Lambda基础设施上,使其与当前系统完全集成.
Data Scientist
Sopra Steria España
- 开发了新的方法来衡量零售客户端的业务成功及其在Python中的实现.
- 使用SQL和Python对零售促销活动进行后期分析,并将结果呈现给利益相关者.
- Optimized SQL queries to extract insights from large tables.
- 重构并优化了一个内部Python包,以提取和可视化大型数据库表的统计信息.
Data Scientist (Master Thesis Student)
Allianz
- Wrote my thesis about machine learning methods to model life tables.
- Performed the preprocessing, analysis, and modeling of data with a size of over 100GB.
- Built and tested an R package for internal usage in the actuarial department.
- 作为官方培训系列的一部分,我在专家面前做了最后的演讲.
- Implemented exhaustive performance optimization of R code using vectorization, parallelization, and optimized packages.
Data Scientist
Allianz
- Implemented and supported extensive interactive data-driven dashboards in R-Shiny.
- 根据客户特点和产品历史,开发企业客户产品推荐系统.
- 建立一个高效的自动化系统,用于基于客户投诉数据的产品或业务流程问题的早期检测.
- 使用Plotly, D3实现了复杂数据的可视化和见解的呈现.js, and R Markdown.
- Performed topic modeling and text mining of client complaint texts using LDA.
- 构建关于机器学习领域的理论和编程包的演示.
- 创建内部编程包,以简化和简化经常使用的数据科学任务.
Researcher
Fraunhofer Institute for Industrial Mathematics ITWM
- Worked on the project Senrisk (Senrisk.Eu /),根据新闻情绪预测公司债券和主权债券的价格波动.
- Built recurrent neural networks in PyTorch to predict financial time series.
- Developed statistical methods for fraud detection in the health insurance industry.
- Implemented a Python package for financial time series prediction, including the integration to a web service.
- 在R Shiny中构建了一个软件原型,以可视化不同样本量在欺诈检测环境中的影响.
Intern
Universidad Técnica Federico Santa María
- 用c#实现基于Black-Scholes模型的财务评估软件.
- Created a detailed report about the theoretical foundations of option price valuation.
- Conducted research related to the Black-Scholes model and financial time series.
Experience
EU Project SENRISK
My part was mainly the implementation of the prediction system. 我们使用了循环神经网络和增强方法,并构建了一个Python包来简化整个过程.
Analysis and Visualization of WhatsApp Chats
http://github.com/l47y/whatsappalyticsMachine Learning Demonstration Tool
http://github.com/l47y/ml_toolAndroid App Course Analyzer
http://github.com/l47y/SiCoursesOn the main page, you have an overview of all courses, and you can export and import a list of the courses. Finally, you can see statistics of the evaluations, 还有一张地图显示了课程的地点,并提供了一些额外的信息. Currently, it is only available in Spanish.
Skills
Languages
Python, R, SQL, C#, Markdown, Kotlin, HTML, CSS
Frameworks
RStudio Shiny, LightGBM, Selenium
Libraries/APIs
Pandas, Ggplot2, XGBoost, Keras, Scikit-learn, Beautiful Soup, NumPy, PySpark, PyTorch, SciPy
Tools
Plotly, Amazon SageMaker, Amazon Athena, Git, LaTeX, Microsoft Excel, PyCharm, Microsoft PowerPoint
Paradigms
Data Science, Business Intelligence (BI), Automation, Testing
Platforms
Jupyter Notebook, RStudio, Amazon Web Services (AWS), Linux, Azure, Anaconda, Databricks, Apache Kafka, Docker, Amazon EC2, Dataiku
Other
Data Analysis, Dashboards, Data Analytics, Applied Mathematics, Mathematics, Dashboard Development, Data Visualization, Machine Learning, Natural Language Processing (NLP), Random Forests, Dashboard Design, Reporting, Data Reporting, GPT, Generative Pre-trained Transformers (GPT), Financial Markets, Financial Data, Big Data, Algorithms, Process Automation, Optimization, Web Scraping, Web Crawlers, Time Series Analysis, Statistical Analysis, Neural Networks, Credit Risk, Loans & Lending, Software Engineering, Data Engineering, Android Development, Streaming Data, Signal Processing, Large Language Models (LLMs), Project Leadership, Microsoft Office, Quantum Computing, Quantum Machine Learning
Storage
Redshift, Databases, SQL Server Management Studio (SSMS), MySQL, MongoDB, Neo4j, Database Management, Graph Databases
Education
Master of Science Degree in Financial and Actuarial Mathematics
Technical University Kaiserslautern - Kaiserslautern, Germany
Spent an Exchange Year in Financial Mathematics
Universidad Técnica Federico Santa María - Valparaíso, Chile
Bachelor of Science Degree in Mathematics
Technical University Kaiserslautern - Kaiserslautern, Germany
Certifications
Quantum Applications Lab
IBM
Quantum Business Foundations
IBM
Neo4j Certified Professional
Neo4j
Big Data Fundamentals with PySpark
DataCamp
Applying SQL to Real-world Problems
DataCamp
How to Work with Toptal
在数小时内,而不是数周或数月,我们的网络将为您直接匹配全球行业专家.
Share your needs
Choose your talent
Start your risk-free talent trial
Top talent is in high demand.
Start hiring