← Back to cohort

Muhammad Zeeshan

FAST · 2023
Email
zeeshansuleman3@gmail.com
Phone
+923225197327
LinkedIn
GitHub

Academic

Program
CGPA
Year
2023
Education
Address
DOB

Verbatim text

The exact text the LLM saw on the page (or the booklet text from the old import). This is what powers semantic search.
ATIONAL UNIVERSITY | I
Muhammad Zeeshan
+923225197327, Zeeshansuleman3@gmail.com
H#37/A, St#7, Alwadi Colony, 17 Meel, Bhara Kahu, Islamabad.
LinkedIn: www.linkedin.com/in/mzeeshn /
Github: github.com/zeeshn99
Education
Bachelor of Science (Data Science) 2023
\Major: Data Science, Artificial Intelligence, Data Mining, Data Warehouse, Distributed Data Engineering, Machine
Learning Operations, Big Data Analytics, Data Analysis and Visualization, Advanced Statistics
Punjab College of Science, Blue Area, Islamabad 2019
|F.Sc (Physics, Chemistry, Mathematics)
MS, G-6/4, Islamabad 2016
(Matriculation (Physics, Chemistry, Electrical)
Projects
Final Project: DriftCach: Enabling Drift in CacheJoin for Near Real Time Data Warehouse [Python, Scikit-Sklearn, SQL, MySQL,
Jupyter Notebook, ARIMA, Plotly]
Research oriented project to optimize semi-stream join operations between high-speed stream data and master data in CacheJoin
algorithm using machine learning.
Semester Projects:
[Meme Sentiment Analysis [Python, Pytorch, Neural Network, Jupyter Notebook, Pandas, Flask] :
Developed multi-modal Neural Network to classify the sentiment of memes via image and text processing.
[Diabetes Detection using Eye Images [Python, Pytorch, Neural Network, Jupyter Notebook, Pandas]:
Segmented eye images were used with Convolutional Neural Networks to determine whether a person has diabetes or not.
Automated Answer Evaluation [Python, Transformers, Jupyter Notebook] :
\Created a semantic similarity-based algorithm which evaluated answers of students on the basis of how close they were to the real
nswer.
IESHJOIN: Near Real time Semi-stream joins in Data warehouse [JAVA, SQL, MySQL] :
Implemented MESHJOIN algorithm to join multiple stream data with multiple master data records and populated a Data Warehouse.
\Multi-Node Hadoop Clusters [Azure, Python, Hadoop]:
\Created multi-node cluster on Azure to Map-Reduce large files using the Hadoop framework.
|GYM Database Development [PHP, SQL, HTML, CSS]:
Designed and implemented a relational database fit for a gym to handle clients, trainers, equipment, etc.
Work Experience
\Undergraduate Research Assistant, Datalnsight Lab, Islamabad. August 2022 - Present
(Optimized semi-stream join algorithms in Data Warehousing using Time series forecasting.
eveloped an evaluation metric to evaluate empathy in dialogues utilizing Bi-Encoder Models with
ttention and prepared the dataset for future research in the field of Empathy
De Research Intern, AIM Lab, Islamabad June 2022 - August 2022
Di
Skills & Tools
Professional Skills Leadership, Team player, Writing, Time Management
Technical Skills Python, R, SQL, C/C++, JAVA, JavaScript, Scikit-Sklearn, Pytorch, NLTK, spaCy, Pandas, ARIMA, NumPy,
Matplotlib, Plotly, Hadoop, Spark, Kafka, Anaconda, Jupyter, MySQL, MongoDB, DynamoDB, Visual Studio,
isual Code, Eclipse
Achievements
Received Bronze medal for 3rd position in batch, Spring 2022, Fall 2022.
Dean's Honor List - Fall 2022.
Runner-up position in the DataQuest NASCON’23 Data Science competition.
Finalist of Datathorn at NaSCon’22 in 2022.
Publication: “EMP-EVAL: A Framework for Measuring Empathy in Open Domain Dialogues”
Trainings / Certification
ARIMA Models in Python [DataCamp]
Natural Language Processing with Attention Models [Coursera]
Natural Language Processing with Classification and Vector Spaces [Coursera]
Supervised Learning with scikit-learn [DataCamp]
Python Data Science Toolbox [DataCamp]
Interests
Sports, Playing video games , Reading books.

AI enrichment

Muhammad Zeeshan is a recent Data Science graduate with experience as a research assistant focusing on data warehousing, machine learning, and NLP. He has practical project experience in building neural networks, optimizing algorithms, and managing big data clusters using Python, SQL, and cloud technologies.
Skills (AI)
["Python", "SQL", "Machine Learning", "Deep Learning", "PyTorch", "Scikit-learn", "Data Warehousing", "NLP", "Hadoop", "Spark", "Kafka", "Java", "R", "C/C++", "Data Analysis", "Visualization"]
Status: ai_done
Provenance
Source file:
Created: 1777726226