Merve Acar, Developer in Santa Clara, CA, United States
Merve is available for hire
Hire Merve

Merve Acar

Verified Expert  in Engineering

Data Scientist and Software Developer

Location
Santa Clara, CA, United States
Toptal Member Since
March 11, 2019

Merve是一位经验丰富的机器学习工程师，他喜欢揭示数据的故事并构建预测模型，并具有设计和实现提取管道的良好记录, validating, cleaning, transforming, and modeling data. 她热衷于解决现实世界中的行业问题，并渴望接受新的挑战和机遇.

Machine LearningData CleaningExploratory Data AnalysisWeb ScrapingArtificial Intelligence (AI)SQLPythonScikit-learnPandasMicrosoft Power BIStatisticsSoftware EngineeringData AnalyticsData MiningDeep LearningSeabornObject DetectionVersion Control Systems MatplotlibTime Series AnalysisYou Only Look Once (Yolo)HaskellRapidMinerPlotlySentiment Analysis

Portfolio

Trust & Safety Laboratory
Python, SQL, Amazon Web Services (AWS)， Amazon EC2, Amazon S3 (AWS S3)...
Turkish Aerospace Industries
计算机视觉，数据挖掘，数据科学，深度学习，Git, Jira, Python...
Vitus Commodities
Slack, Jira, Git, Plotly, Selenium, RapidMiner, Keras, PyTorch...

Experience

MySQL - 7 yearsPython - 6 yearsMachine Learning - 5 yearsData Mining - 5 yearsData Science - 5 yearsPyTorch - 4 yearsDeep Learning - 4 yearsTableau - 2 years

Availability

Part-time

Preferred Environment

Git, PyCharm, Jupyter Notebook, Linux, Windows, Amazon EC2, Jira, Slack

The most amazing...

...我开发的自动化机器学习工具利用元学习的能力来选择最优算法及其参数, adapting to any task.

Work Experience

Data Analyst

2023 - PRESENT
Trust & Safety Laboratory
  • 自动收集从多个事实核查网站传播错误信息的社交媒体账户.
  • 利用hug Face的CLIP模型进行零射击学习，检测图像中的有害内容.
  • 执行分析可视化不良行为者和他们的朋友的朋友网络图.
  • Translated client requirements into interactive dashboards in Tableau.
Technologies: Python, SQL, Amazon Web Services (AWS)， Amazon EC2, Amazon S3 (AWS S3), Protobuf, Okta, Twitter API, Beautiful Soup, NetworkX, Gephi, Snowflake, OpenAI GPT-3 API, Tableau, Bazel, Databases, Data Cleaning, Data Analytics, Social Media

Data Scientist

2019 - 2022
Turkish Aerospace Industries
  • 开发了一个基于仪表板的监控系统，利用IP摄像机记录改善工厂的工作流程. 应用视频和图像处理算法使用OpenCV库与目标检测和目标跟踪算法.
  • 建立一个基于lstm的模型来识别人们的行为并改进工厂的工作流程.
  • 使用ARIMA和LSTM算法开发了一个预测性维护模型，该模型使用飞机部件的时间序列数据来洞察飞机部件的故障. Applied data manipulation, analysis, and visualization.
Technologies: 计算机视觉，数据挖掘，数据科学，深度学习，Git, Jira, Python, Object Detection, Object Tracking, Time Series Analysis, MySQL, PostgreSQL, PyTorch, Long Short-term Memory (LSTM), Bash Script, Keras, PyCharm, Windows, Jupyter Notebook, Neural Networks, Scikit-learn, Matplotlib, Visualization, Seaborn, SQL, Data Visualization, Software Engineering, Convolutional Neural Networks (CNN), Data Analysis, Machine Learning, Python, Pandas, Data Modeling, Data Processing, Supervised Machine Learning, Regression, Classification, CSV, Reports, Data Scientist, OpenCV, You Only Look Once (YOLO), Data Cleaning, Data Analytics, Artificial Intelligence (AI)

Machine Learning Engineer

2016 - 2019
Vitus Commodities
  • Took part in several data scraping projects using Selenium, API calls, the requests library, and more.
  • Created reports on Microsoft Power BI for data visualization.
  • 使用Python和Keras实现多层感知器模型来预测未来几天英国的天然气需求.
  • 部署LSTM模型，预测土耳其未来几天的电价.
  • 实现了一个scraper来获取和操作GFS天气数据，以用作模型训练的源.
  • 研究了深度学习方法，以提高当前工作模型对时间序列数据的性能.
  • 实施了一个异常值检测项目，该项目由基于概率和聚类的算法以及自动编码器方法组成，用于检测与英国天然气需求相关的极端天数.
Technologies: Slack, Jira, Git, Plotly, Selenium, RapidMiner, Keras, PyTorch, Microsoft Power BI, MySQL, Python, Amazon Web Services (AWS), Amazon S3 (AWS S3), Amazon EC2, Long Short-term Memory (LSTM), XGBoost, Data Visualization, Data Scraping, Time Series Analysis, PyCharm, Windows, Neural Networks, Scikit-learn, Matplotlib, Slack API, Seaborn, SQL, Amazon RDS, Data Mining, Convolutional Neural Networks (CNN), Data Analysis, Machine Learning, Predictive Modeling, Pandas, Data Modeling, Data Processing, Web Scraping, Supervised Machine Learning, Regression, Classification, Decision Trees, APIs, Statistical Analysis, Exploratory Data Analysis, Databases, Data Cleaning, Data Analytics, Artificial Intelligence (AI)

Machine Learning Engineer

2016 - 2017
Independent Work
  • Implemented data preprocessing, data imputation, feature extraction, and model creation modules for the Vitriol project using Scala.
  • 研究并测试了一种元学习策略，用于使用Scala和Spark为给定问题预测具有最佳参数的最佳模型.
  • 使用Python实现了一个解析器来处理来自不同来源的非结构化数据.
  • Worked with big data using Apache Spark framework and Scala.
Technologies: Git, PostgreSQL, Spark, Scala, Python, Python 3, Data Science, Spark ML, Matplotlib, Visualization, Seaborn, Data Mining, Data Analysis, Machine Learning, Predictive Modeling, Data Modeling, Data Processing, Supervised Machine Learning, Regression, Classification, Decision Trees, Decision Modeling, Data Cleaning

Software Developer

2015 - 2015
C3S Command Control & Cybernetic Systems
  • 开发连接器可靠性测试软件，控制Linux平台上PCI卡与连接器之间的连接.
  • 开发软件，计算员工在办公室花费的时间.
  • Wrote SQL database queries to analyze an employee's working schedule.
Technologies: MySQL, Python, C++, Linux, PostgreSQL, SQL

Software Test Developer

2014 - 2014
Taleworlds Entertainment
  • Developed automated tests for Mount&Blade: Bannerlord II project.
  • 每天监控测试结果并报告在预发布软件中发现的错误.
  • 执行单元测试和集成测试，以确定游戏场景是否正常工作.
  • Worked within an Agile environment with multiple teams.
Technologies: Git, C++

Software Developer

2014 - 2014
TUBITAK | The Scientific and Technological Research Council of Turkey
  • Developed a parental control tool for Pardus, a Linux distribution supported by the Turkish government.
  • Implemented content filter, usage control, and monitoring modules.
  • Gained experience in open-source development and the security field.
Technologies: PyQt, Bash, Python, Linux, Bash Script

Vitriol

http://senior.ceng.metu.edu.tr/2016/mallorn/
这是一个自动化的机器学习工具，它使用机器学习和数据挖掘技术来预处理数据，并为给定的问题自动选择机器学习模型.

我使用元学习策略来选择最合适的算法及其参数. 本项目采用Spark和Scala编程语言实现大数据处理.

Natural Gas Demand Forecasting

该项目旨在利用几种技术预测英国的天然气需求, such as feature engineering and data augmentation.

首先，我实现了一个极端天气检测模块，将数据标记为极端或非极端. 过采样方法有助于增强极端天气，因为它们只占数据的一小部分. 我还使用多层感知器(MLP)和线性回归模型实现了一个动态加权集成模型，以考虑线性和非线性趋势.

Stock Price Prediction

该项目的目标是预测法兰克福证券交易所的股票价格, including those for BMW and Daimler. 我在PyTorch中构建了RNN, GRU和LSTM模型，因为它是一个时间序列问题.

Denoising of Images

In this project, I mainly implemented various generative networks, 以及它们的组成部分来执行无监督学习，用于生成新的数据样本(图像)和, the denoising of images.

PriceTag

这个项目的目的是利用图片预测几个领域产品的市场价格和相应的市场价值. 我用Python和Keras训练了一个卷积神经网络来预测给定产品的价格.

Pardus Gozcu

This is a parental control tool consisting of content filtering, usage time controlling, usage management (for allowing/blocking a set of software types), and monitoring to watch and report user activities. It is an open-source project developed for Pardus, a Linux distribution, using PyQt, Python, and Bash.
2017 - 2020

Master's Degree in Computer Engineering

Istanbul Technical University - Istanbul, Turkey

2012 - 2016

Bachelor's Degree in Computer Engineering

Middle East Technical University - Ankara, Turkey

FEBRUARY 2023 - PRESENT

Using Python to Access Web Data

Coursera

OCTOBER 2022 - PRESENT

Structuring Machine Learning Projects

Coursera

SEPTEMBER 2022 - PRESENT

Convolutional Neural Networks

Coursera

SEPTEMBER 2019 - PRESENT

Practical Time Series Analysis

Coursera

SEPTEMBER 2019 - PRESENT

Fundamentals of Visualization with Tableau

Coursera

AUGUST 2019 - PRESENT

Google Cloud Platform Big Data and Machine Learning Fundamentals

Coursera

SEPTEMBER 2018 - PRESENT

Neural Networks and Deep Learning

Coursera

NOVEMBER 2016 - PRESENT

Machine Learning Foundations: A Case Study Approach

Coursera

Libraries/APIs

Matplotlib, Scikit-learn, Pandas, PyTorch, Keras, Slack API, XGBoost, OpenCV, Natural Language Toolkit (NLTK), Spark ML, PyQt, Beautiful Soup, TensorFlow, Protobuf, Twitter API, NetworkX

Tools

Microsoft Power BI, PyCharm, Slack, Git, Seaborn, Plotly, Tableau, Jira, Bazel, You Only Look Once (YOLO)

Languages

Python, SQL, Python 3, Bash, Scala, c++， Haskell, Bash Script, R, XML, Snowflake

Paradigms

Data Science

Industry Expertise

Social Media

Frameworks

Selenium, Spark

Platforms

Windows, Linux, Jupyter Notebook, RapidMiner, Amazon EC2, Amazon Web Services (AWS), Gephi, AWS Lambda

Storage

PostgreSQL, MySQL，数据管道，数据库，Amazon S3 (AWS S3)， JSON

Other

Machine Learning, Predictive Modeling, Data Processing, Web Scraping, Google Colaboratory (Colab), Regression, Classification, Decision Trees, Artificial Intelligence (AI), CSV, Exploratory Data Analysis, Data Cleaning, Computer Vision, Metric Learning, Time Series, Data Mining, Visualization, Deep Learning, Statistics, Object Detection, Object Tracking, Time Series Analysis, Data Visualization, Software Engineering, Convolutional Neural Networks (CNN), Image Analysis, Neural Networks, Data Structures, Data Analysis, Data Modeling, Version Control Systems, Models, Modeling, Communication, Data Analytics, APIs, Data, Unsupervised Learning, Supervised Machine Learning, Decision Modeling, Data-driven Decision-making, Data Engineering, Dashboards, Reports, Data Scientist, Statistical Analysis, Remote Sensing, Natural Language Processing (NLP), Cloud Services, Design, Machine Learning Automation, Gated Recurrent Unit (GRU), Generative Adversarial Networks (GANs), Long Short-term Memory (LSTM), Data Scraping, Feature Analysis, Amazon RDS, Sentiment Analysis, GPT, Generative Pre-trained Transformers (GPT), Okta, OpenAI GPT-3 API

Collaboration That Works

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.

1

Share your needs

在与Toptal领域专家的电话中讨论您的需求并细化您的范围.
2

Choose your talent

在24小时内获得专业匹配人才的简短列表，以进行审查，面试和选择.
3

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring