-
Experience
Seedcode.io - Aug 2020 - Present
Data Science Intern
Found out best-performing use cases for building a financial model on PSX by performing R&D by reading several research papers and articles.
Analyzed the best-performing markets by setting different thresholds by writing scripts for data collection, populating the database for analysis, then visualizing their trends over time.
Deployed the model using Django, and created a dashboard to provide actionable insights to the user, by comparing graphs and identifying the potential investment opportunities.
Optimized migration by writing an automation script to run several files in a sequence to make code 2x easier to migrate into a new system.
Refactored and restructured code to make it understandable for other developers and easy to scale in the future.
Skills and Tools: Python, vs code, MongoDB, pymongo, beautiful soup(bs4), requests, Django, Javascript, jupyter notebook, ta-lib, lucid charts.
-------------------------------------------------------------------------
Bytecorp.io - April 2020 - Aug 2020
Machine Learning Intern
The only intern out of other 5 AI/ML Interns to work on a client-facing project which included:
Implemented and suggested new implementable strategies for the financial model by communicating directly with clients, reporting, & updating them about the progress to constructively search for the best solution.
Wrote scripts in python for automating more than 30 strategies.
Ran 200+ experiments for trying out different combinations of best-performing features, logged them into a sheet, and did analysis through different visualizations.
Performed analytics on 2-3 demo datasets to explore computer vision, and good approaches for improving code quality and efficiency to implement on the realtime project ‘IDEM’.
Skills and tools: Python, GoogleColab, pgSQL, Google Analytics & data studio, Advanced report making, ta-lib, Tensorflow, Keras, pandas, and sklearn.
-------------------------------------------------------------------------
VentureDive - June 2019 - July 2019
Software & Web Intern
Collaboration with a team to build Shopping Cart and Todo App in which I learned and wrote the Reactjs code for the first time and integrated my app with a backend in Node.js and MongoDB, then deployed the app on Surge.
Got to explore how VentureDive’s online assessments and recruitment site works.
Performed documentation and made a report and presentation to elaborate on each method and step.
Skills and tools: VScode, npm, Javascript, ReactJS, Git, GitHub, HTML, CSS, and MongoDB.
-
Projects
PRODUCT TITLE CHAINED CLASSIFICATION(2020) -- Combined the concepts of Machine Learning, DL(Recurrent Neural Networks architecture), and Information Retrieval techniques with complete data and natural language preprocessing pipeline to solve multi level-category classification(Lazada Dataset with 37000 title records) problem with 87% accuracy. [Tensorflow, Keras, Python, Google Colab, sklearn, pandas].
CV-RECOMMENDER APP(2019) -- Followed Agile Software Development Life Cycle(SDLC) approach to recommend CVs based on their score(TFIDF) when Recruiter posts a job with the number of required employees and job descriptions. The app works like an ATS which is used for recruitment purposes, treating documents as vector spaces. [HTML, CSS, JavaScript, Flask, MongoDB, and ReactJS, JWTdecode, pdfminer].
COMPARISON B/W MULTI-THREADS & MULTI-PROCESSES(2019) -- Compared 5 series to exhibit contrast between multi-threads and multi-processes in Ubuntu (Linux Operating System). [Linux/Unix- Ubuntu, C, fork methods, VMware].
UNIVERSITY MANAGEMENT SYSTEM-Desktop App(2018) -- Created an advanced network of University Management System with complete management dashboards for faculty, departments, & students. [C#, Visual Studio 2017, SQL Server].