Renee Ahel
Verified Expert in Engineering
机器学习开发人员
Renee is a data scientist with over 12 years of experience, and five years as a full-stack software engineer. 超过12年, 他曾在国际环境中工作, with English or German as a working language. 其中包括为德国和奥地利客户公司远程工作四年,以及作为德国电信国际分析团队成员远程工作九个月.
Portfolio
Experience
Availability
首选的环境
RStudio, Linux, Windows
最神奇的...
...我建立的预测模型是预测电信客户同时使用竞争对手服务的可能性的模型.
Work Experience
自由数据科学家
自由数据科学家
- 从咖啡店的登记表中收集和展示数据,并得出顾客的行为模式,使饮料生产商的营销团队能够更好地做出如何销售的决策, when, 以及如何投资营销预算.
- Developed a suite of spend classification models using R language (data.table, ggplot2, xgboost包), NLP技术和XGBoost分类器, used AWS Lambda and AWS API Gateway for production deployment.
- 设计了一个专家系统,使客户能够提供专业的采购知识,为客户制定采购策略.
- 撰写专家系统解决方案的大量文档,作为专利申请的基础.
- Developed a reporting database based on PostgreSQL, using Power BI as frontend. Implemented a data pipeline using R language (tidyverse, jsonlite, 使用Square和Brushfire api与客户端的Square和Brushfire帐户集成. The PowerBI dashboards covered business sales, inventory and labor business areas.
- 为客户撰写基于边缘的机器学习解决方案的技术白皮书.
- 在多个IT会议和聚会上发表了“数据可视化101”研讨会. 研讨会的重点是基本的数据可视化原则-从人类视觉认知如何工作, to basic data visualization forms and most frequent mistakes. There was also an emphasis on creating effective dashboards.
Data Scientist
俄罗斯电信公司., Zagreb, Croatia – part of Deutsche Telekom
- Served as a member of an international analytics team of Deutsche Telekom, 在克罗地亚远程工作, 在德国与球队经理会面. I've used Oracle SQL on the Oracle 12c data warehouse as a data source.
- 固定线路流失预测模型能够早期发现有可能终止服务的客户, 启用预防性保留操作. 我在Oracle 12c数据仓库上使用Oracle SQL作为数据源,并使用SPSS Modeler进行建模和部署到生产环境中.
- 改进的家庭检测显着增加了客户家庭的潜在基础, necessary for offering the companies' flagship product. 我在Oracle 12c数据仓库上使用Oracle SQL,在Cloudera大数据平台上使用Hive SQL作为数据源, H2O用于建模,R(数据).table, H2O, cronR, ggplot2 packages) for additional data preparation, 部署到生产和监控.
- 开发了关键产品的倾向模型,显著提高了转化率. 我在Oracle 12c数据仓库上使用Oracle SQL,在Cloudera大数据平台上使用Hive SQL作为数据源, H2O用于建模,R(数据).table, H2O, cronR, ggplot2 packages) for additional data preparation, 部署到生产和监控.
Data Scientist
Vipnet LLC, Zagreb, Croatia – part of América Móvil
- 构建了一个推荐引擎,为每个业务客户生成个性化的产品建议, by combining internal and third-party data on business customers. I've used Oracle SQL on an Oracle 12c data warehouse as a data source.
- 通过结合公开和内部公司数据,以极高的准确度估计克罗地亚整个领土的个人地址级别的固定网络扩展潜力. 它使固定网络的投资能够最优地分配到最具商业潜力的地区, 最低的建筑成本. I've used Oracle SQL on an Oracle 12c data warehouse as a data source.
- 通过结合市场研究数据和内部数据,训练了一个模型来估计客户拥有竞争对手订阅的可能性. It provided a potential base for cross-sell/up-sell activities. I've used Oracle SQL on an Oracle 12c data warehouse as a data source, SAS for data preparation and deployment to production, SAS企业矿机用于建模.
- Analyzed customer recharge behavior by creating a recharge based segmentation. 这种分割使得引入更适合客户需求的新凭证面额成为可能. I've used Oracle SQL on an Oracle 12c data warehouse as a data source, SAS for data preparation and deployment to production, SAS企业矿机用于建模.
- Developed a model predicting which customers are most likely to buy data options. It enabled optimal customer targeting when offering data options. I've used Oracle SQL on an Oracle 12c data warehouse as a data source, SAS for data preparation and deployment to production, SAS企业矿机用于建模.
- 通过对采购交易数据进行购物篮分析,分析小企业的购买行为. 它提供了可供销售使用的新见解. I've used Oracle SQL on an Oracle 11g data warehouse as a data source, SAS for data preparation and deployment to production, SAS企业矿机用于建模.
- Created models predicting churn for the small business segment. They enabled early detection of customers with potential to terminate the service, 启用预防性保留操作. I've used Oracle SQL on an Oracle 12c data warehouse as a data source, SAS for data preparation and deployment to production, SAS企业矿机用于建模.
- Collaborated with the data warehouse team to redesign the data science data mart. 我们参与了数据源、数据转换和数据库表格式的定义. Following the implementation, we did intensive data quality testing. 生成的数据集市更适合我们的需求,并且具有可跟踪的数据源, which helped to quickly resolve data quality issues. I've used Oracle SQL on an Oracle 11g data warehouse as a data source.
- 在DWH重新设计项目期间,我认识到业务需要一个独特的客户数据集. 我编写了一个详细的规范,其中包含有关数据处理和数据质量改进的复杂规则. 在此过程中,我分析了两个包含客户数据的相关源系统. The resulting unique customer data set is used for company-wide reporting, CRM campaigning and has enabled a tenure-based customer loyalty program. I've used Oracle SQL on an Oracle 11g data warehouse staging area as a data source.
- Implemented an e-bill affinity prediction model, which predicted which residential customers are most likely to switch to e-bills. It enabled the billing department to speed up the adoption of e-bills. I've used Oracle SQL on an Oracle 11g data warehouse as a data source, SAS for data preparation and deployment to production, SAS企业矿机用于建模.
商业智能开发人员
SoftPro Tetral LLC,萨格勒布,克罗地亚
- Contributed to development work on CubePlayer application, an OLAP client for Analysis Services 2000/2005 using VB.NET 2.0、MDX和ComponentOne for .NET 2.0.
- 介绍ClickOnce部署, Subversion源代码控制和Trac问题跟踪器集成到CubePlayer开发项目中.
Team Lead
Ekobit LLC,萨格勒布,克罗地亚
- 发达国家税务部门, 一个针对德国消费者市场的报税应用程序,是为德国客户公司Lexware GmbH开发的. I've used C# 2.. NET框架.0、SQL Server 2000, MS Access 2000 and C++/MFC.
- Lead a team working remotely on full stack development of Taxman.
软件工程师
Ekobit LLC,萨格勒布,克罗地亚
- Developed MAWIS, an ERP system used in the waste disposal industry developed for a German client, MOBA AG. Work involved maintenance and implementation of new functionality. 我用过c++ /MFC和SQL Server 2000.
- Built MAWIS-online, a lightweight web-frontend for the MAWIS ERP system using C# 2.0, .NET Framework 2.0、SQL Server 2000.
- Created MAWIS.NET, a framework for import/export of data to/from MAWIS ERP system using C# 2.0, .NET Framework 2.0和SQL Server 2000.
- Worked remotely on all above mentioned software development projects.
软件工程师
Okit LLC,萨格勒布,克罗地亚
- 开发ZAD3-online, 一个web应用程序,用于登记和跟踪低压电网故障,为克罗地亚电力公司使用c# 1开发.0, ASP.NET 1.1 and Oracle 9i.
- Built ZAD3, 为克罗地亚电力公司开发的用于登记和跟踪低压电网故障的Windows应用程序, 使用c++ /MFC和msaccess2000.
- Programmed ZAD1, 使用c++ /MFC为克罗地亚电力公司开发的用于登记和跟踪高压和中压电网故障的Windows应用程序, MS Access 2000和Oracle 8i.
Experience
Insights From Web Shop Sales Data: A Demo Data Science Project
http://github.com/reneeahel/online-retail-data-analysis分析的很大一部分由数据清理和基本探索性分析组成, as usually is the case with data science projects. 在这些基本步骤之后, 我在Spark上使用机器学习算法来发现更复杂的客户行为模式, like which products are frequently purchased together.
Project deliverables are publicly available data science notebook:
http://rpubs.com/reneeahel/OnlineRetailAnalysisDemo
和一个交互式web应用程序:
http://renee-ahel.shinyapps.io / OnlineRetailDemo /
aimed at bringing the project results quickly to the business users.
Technologies used: R, tidyverse, sparklyr, and Spark.
自动关键短语提取系统
使用的技术和语言:SQL Server
Education
Master of Science Degree in Machine learning
萨格勒布大学电子工程与计算机学院-克罗地亚萨格勒布
Bachelor of Science Degree in Machine learning
萨格勒布大学电子工程与计算机学院-克罗地亚萨格勒布
Certifications
使用数据进行数据操作.table in R
Datacamp
数据科学家与Python轨道
Datacamp
Python深度学习入门
Datacamp
Python网络分析入门
Datacamp
用数据连接数据.table in R
Datacamp
Manipulating Time Series Data with xts and zoo in R
Datacamp
R中的并行编程
Datacamp
Python程序员跟踪
Datacamp
监督学习与scikit-learn
Datacamp
带数据的时间序列.table in R
Datacamp
Python中的无监督学习
Datacamp
编写高效的R代码
Datacamp
Python中的统计思维(第2部分)
Datacamp
带有散景的交互式数据可视化
Datacamp
Introduction to Data Visualization with Python
Datacamp
Python中的统计思维(第1部分)
Datacamp
Python数据库入门
Datacamp
使用pandas操纵数据框架
Datacamp
合并dataframe和pandas
Datacamp
熊猫基金会
Datacamp
清理Python中的数据
Datacamp
用Python导入数据(第2部分)
Datacamp
用Python导入数据(第1部分)
Datacamp
中级Python数据科学
Datacamp
Python简介
Datacamp
机器学习 with Tree-Based Models in R
Datacamp
Python数据科学工具箱(第2部分)
Datacamp
Python数据科学工具箱(第1部分)
Datacamp
康达基本课程
Datacamp
Shell数据科学入门
Datacamp
Sequence Models
Coursera
深度学习专业化
Coursera
神经网络和深度学习
Coursera
改进深度神经网络:超参数调整、正则化和优化
Coursera
卷积神经网络
Coursera
在R中使用sparklyr介绍Spark
Datacamp
用Shiny在R中构建Web应用程序
Datacamp
Python 3教程
Sololearn
Predictive Modeling Using Logistic Regression
SAS Institute
Applied Analytics Using SAS企业矿机 5.3
SAS Institute
SAS企业指南 - ANOVA, Regression and Logistic Regression
SAS Institute
SAS宏语言
SAS Institute
Predictive Modeling Using SAS企业矿机 5.1
SAS Institute
微软认证应用程序开发人员
Microsoft
微软认证解决方案开发人员
Microsoft
微软认证专家
Microsoft
Skills
Libraries/APIs
Tidyverse, Ggplot2, XGBoost, REST APIs, JSON API, ADOMD.NET, 微软基础类(MFC)库, Pandas, NumPy, Matplotlib, Scikit-learn, 微软基础课程(MFC)
Tools
Microsoft Excel, Office 2016, SAS企业矿机, SAS企业指南, SPSS Modeler, Microsoft Power BI, Google Sheets, Subversion (SVN), Trac, Dplyr, Readr, Tibble, sparklyr, DataTables, Cron, Cloudera, Microsoft Access, Git, GitHub
Languages
R, SQL, SAS, XML, MDX, Visual Basic .NET (VB.NET), C++, C#, Python 3, Python, Bash, Bash Script
Paradigms
DevOps, Data Science, Database Design, Business Intelligence (BI)
Platforms
AWS Lambda, RStudio, Windows, H2O深度学习平台, Amazon EC2, H20, 亚马逊网络服务(AWS), Linux
Storage
Oracle SQL, Databases, 公司数据库, Oracle RDBMS, 数据库建模, JSON, PostgreSQL, Oracle9i, SQL Server 2008, SQL Server 2000, Apache Hive, MySQL
Frameworks
RStudio Shiny, .. NET, Hadoop, ASP.. NET, Apache Spark, Spark
Other
工程数据, 软件开发, 机器学习, Data Mining, Data, Data Analysis, Data Modeling, Documentation, Requirements & 写作规范, & Editing, API文档, Algorithms, Data Queries, 计算语言学, 自然语言处理(NLP), 正则表达式, Visualization, Presentations, SAS Macros, Base SAS, 亚马逊API网关, Ghostwriting, APIs, GPT, 生成预训练变压器(GPT), ComponentOne, Purrr, Big Data, Architecture
如何使用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
选择你的才能
开始你的无风险人才试验
对顶尖人才的需求很大.
Start hiring