Skip to content
View ArdaKaymaz's full-sized avatar
πŸ’­
Thinking about datasets...
πŸ’­
Thinking about datasets...

Block or report ArdaKaymaz

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ArdaKaymaz/README.md

Hi πŸ‘‹, I'm Arda Kaymaz

A passionate data scientist from Turkey

ardakaymaz

  • πŸ’» I'm a Data Scientist and a Data Analyst with 4+ years of experience and a Master of Science degree.

  • ⭐ Co-Founder of Data Jungle 🌴 (LinkedIn)

  • ⚑ Python programming

  • πŸ’ͺ🏻 I'm specialised in Artificial Intelligence πŸ€–, Machine Learning 🦾, Deep Learning 🧠, Time-Series πŸ•’πŸ“ˆ, Statistics πŸ“Š and Big Data⭐

  • ⚑ SAS Base SAS, SAS/STAT, SAS/GRAPH

  • πŸ“« How to reach me [email protected]

Connect with me

ardakaymaz

🧾 Projects

Cat-Dog Classifier App 🐱🐢 (App Link)

β€’ The project aims to develop an image processing model with pre-trained models named MobileNet, VGG16 and ResNet50.
β€’ The project involves utilizing image processing, Mlflow, fine-tuning, TensorFlow, Keras and Streamlit for rapid prototyping and deployment.
β€’ The project was successfully completed with an accuracy of 97.14%.

Apache vs The Fraudster πŸ•΅πŸ»β€β™€οΈβš‘

β€’ The project aims to develop a fraud detection model with big data technologies such as Apache.
β€’ The project involves utilizing Apache Hadoop, Apache Hive and Apache Spark.
β€’ The project was successfully completed with recall of 78.8% and precision of 90.0%.

Scaling, Depth, and Epochs: A Model Comparison Study πŸ“Š

β€’ The study aims to bring a deep understanding about artificial neural networks’ training and prediction process.
β€’ The study involves utilizing TensorFlow and SciKit-Learn.
β€’ The study was resulted in a 1450% lower MAE value and in a 182% lower model weight variation.

Enefit - Predict Energy Behavior of Prosumers (Ongoing) πŸ€πŸ’‘

β€’ The project aims to address Enefit’s energy production and consumption forecast problem.
β€’ The project involves utilizing Apache Hadoop, Apache Spark, Docker, Kubernetes, Flask and auto-regressive time-series forecasting.

Factors Affecting Survivability In Japanese Quail (Coturnix coturnix Japonica) πŸ₯❀

β€’ The study aims to develop statistical risk models to predict survivability and adaptability traits, life-span forecasting, estimating the effect of genetic and environmental factors, and estimating genetic parameters.
β€’ The study involves utilizing hypothesis testing, auto-regressive time-series forecasting and statistical learning models.
β€’ The study has provided insights into the survival abilities of more than 64,000 species.

πŸ’» Tech Stack:

NumPy Pandas scikit-learn TensorFlow PyTorch mlflow Matplotlib LINUX Apache Apache Hive Apache Spark Apache Hadoop Canva Scipy MicrosoftSQLServer

github contribution grid snake animation

Popular repositories Loading

  1. Customer_Segmentation_Using_RFM_Analytics Customer_Segmentation_Using_RFM_Analytics Public

    Python 10

  2. CLTV_Prediction-with-BG-NBD-and-Gamma-Gamma-Model CLTV_Prediction-with-BG-NBD-and-Gamma-Gamma-Model Public

    Python 9

  3. AB_Testing AB_Testing Public

    Python 9 1

  4. House_Price_Prediction_ML_Pipeline House_Price_Prediction_ML_Pipeline Public

    Python 9 1

  5. ArdaKaymaz ArdaKaymaz Public

    8

  6. CRM_Coffee_Beans_Sales CRM_Coffee_Beans_Sales Public

    Forked from Argetlam84/CRM_Coffee_Beans_Sales

    Python 8