Hi, I'm Sikandar Hayat.

I am a Data Scientist with an Computer Systems engineering background. I have completed the coursework for my Bachlor degree in Computer Systems Engineering at University of Engineering and Technology, Peshawar., Pakistan. My Final Year Project title is "Medical Based Brain Anomly Detection Using Deep Learning".I have hands-on expertise with Python, SQL, and Power BI. I am a complete team player with excellent communication and problem-solving skills.

Find me on...


Learn about what I do

Here's all the stuff I do.

Data Analysis with Python

Hands-on expertise on cleaning, pre-processing, and analyzing data using SQL, Pandas, Numpy, Matplotlib, Seaborn, and Plotly.

Dashboards with Plotly Dash and Power BI

Experience with preparing reports and making dashboards for the targeted audiences in Dash and Power BI.

Machine Learning and Deep Learning

Completed regression, classification, clustering, neural networks, convolution neural networks projects in Python using Scikit-Learn and Tensorflow Keras.

Web Devolpment with Django

Designed full fledged websites using Python Django framework, Html and CSS.

Computer Vision and Open CV

Synthetic Image Generation using GANs and Image Classfication Using CNN. Good Knowledge of Image Segmentation, Classification, restoration and generation models.

Here are some of my projects.

Email spam detection using naive Bayes

With Bayes' Rule, we want to find the probability an email is spam, given it contains certain words. We do this by finding the probability that each word in the email is spam, and then multiply these probabilities together to get the overall email spam metric to be used in classification and achive 97% accuracy.

Maven Restaurant Analysis

Created a 1-page dashboard for the Maven Restaurant highlighting all the important metrics from the consumers and restaurant perspective.

Cancer Prediction using SVM

Predicted whether the person has Cancer or not using Support Vector Classifier (SVC) and GridSearchCV in Scikit Learn with an acurracy of 77% and deployed the model using Plotly Dash.

MNIST Digit Classification in Keras

Classified famous MNIST Handwritten Digit Dataset using Artificial Neural Network and Convolutional neural network in Tensorflow Keras with an accuracy of 92.6% without a hidden layer and 97.4% with one hidden layer in the model.

© Sikandar Hayat


Email: sikandarmir4@gmail.com


Contact: +923450940520