Freelancers using Python in Maharashtra

Freelancers using Python in MaharashtraFreelancers using Python in Maharashtra

Projects People

I’m an AI & Machine Learning engineer with expertise in deve

I’m an AI & Machine Learning engineer with expertise in deve

Cover image for Everyone's building AR filters and

Everyone's building AR filters and calling it "computer vision magic." Almost nobody's asking what's actually happening underneath — that most of these effects are just clever masking, not detection. Here's proof. I built an invisibility cloak that runs entirely in the browser, no green screen, no chroma key, no model training. https://github.com/AnuragNagare/Ghost-frame

4

2

210

Cover image for What your attention heatmap isn't

What your attention heatmap isn't telling you Everyone's staring at attention heatmaps and calling it "interpretability." Almost nobody's asking whether a single attention map actually tells you what the model used to make its decision. It doesn't. Not on its own. A raw attention map from layer 8 shows you what layer 8 attended to. It says nothing about how that signal got mixed, diluted, or overwritten by every layer before and after it. Attention rollout fixes this — and I built a walkthrough to show why it matters. Here's what makes it more than a "pretty heatmap" demo: Instead of visualizing one layer's attention, I traced how information actually flows through the full transformer stack. → Every layer's attention matrix is extracted, per head, per token → Multi-head attention is averaged, then combined with the residual connection (identity + attention) — this is the step most tutorials skip, and it's the one that actually matters → The combined matrices are matrix-multiplied layer by layer, rolling attention forward from input to output → The result: a single map showing genuine token-to-token influence across the entire network, not just one layer's snapshot The overlay shows you everything: → Per-layer attention vs. rolled-out attention, side by side → Token importance scores overlaid directly on the input text → A comparison view: which tokens raw attention says "matter" vs. which ones rollout says actually matter → Head-level breakdown so you can see which heads specialize vs. which are noise No black box. No "trust me, the model looked here." Just linear algebra, applied honestly across every layer instead of cherry-picking one. Built with PyTorch + HuggingFace Transformers + Matplotlib. Runs on any pretrained transformer, fully offline. ⚠️ Important: attention rollout is an approximation, not ground truth. It assumes attention is the primary information pathway, which ignores MLP layers and can still mislead for very deep models. Treat it as a debugging lens, not proof of causality.

0

69

Cover image for Everyone's racing to add biometrics

Everyone's racing to add biometrics to logins. Almost nobody's asking what happens when you can't — or shouldn't — touch the sensor. Shared kiosks, clinical settings, accessibility needs, hygiene-sensitive environments. Fingerprint readers and face unlock assume contact or a stored faceprint. Sometimes you want authentication that touches nothing and stores no biometric image of you at all. So I built GestureAuth — a contactless authentication system where your "password" is a sequence of hand gestures performed in front of a standard webcam.

1

63

Cover image for Everyone's talking about AI in

Everyone's talking about AI in healthcare. Nobody's building low-cost tools for the people who actually need early answers. Neurologists are overbooked. Clinical tremor assessments require in-person visits, specialist equipment, and months of waiting. The 10 million people living with Parkinson's globally and the millions more who don't yet know have no accessible way to flag early symptoms from home. So I built TremorLens a real-time hand tremor detection tool that runs entirely on a standard webcam. Here's what makes it more than just a webcam project: Instead of simple motion detection, I built a full signal processing pipeline on top of computer vision. MediaPipe tracks 21 hand landmarks per frame. The index fingertip's x/y displacement is buffered across a 3-second rolling window. scipy FFT then decomposes that signal into its frequency components and flags dominant activity in the 4–6 Hz range clinically associated with Parkinson's resting tremors. The live overlay shows you everything: → Real-time FFT power spectrum with the tremor zone highlighted → Dominant frequency readout in Hz with a 10-frame rolling average for stability → Color-coded STABLE / TREMOR DETECTED indicator → Fingertip displacement graph and movement trail → Auto-saved CSV session log timestamp, frequency, amplitude, tremor flag every session

0

55

Abu Aasif Ansari

Bhiwandi, India

I build AI agents & internal tools that act on data

13: Followers

I build AI agents & internal tools that act on data

Cover image for Ask My Docs — RAG-Based AI Chat Agent

Ask My Docs — RAG-Based AI Chat Agent

0

1

Cover image for Sounds Like AI? — AI Writing Authenticity Checker

Sounds Like AI? — AI Writing Authenticity Checker

0

1

Cover image for Project Overview This is a personal portfolio and services s...

Project Overview This is a personal portfolio and services site built for a working freelancer — myself — as part of the Make It Real Challenge. I'm a data visualization specialist and AI dashboard developer, and I wanted the site itself to reflect that work rather than just describe it. So instead of stock photography and generic copy, every visual on the site is a real screenshot from a project I've actually shipped. The Concept Most freelance portfolio sites lean on polished lifestyle photography — laptops on wooden desks, people in blazers looking thoughtfully at monitors. I wanted to flip that: let the actual product screens do the talking. The site is built around a simple idea — "solutions built on data, not guesswork" — and that shows up literally in the visuals, not just the copy. What's on the site Homepage: A direct hero statement ("I Turn Messy Data Into Decisions") backed immediately by a real dashboard screenshot from my Anomaly Review & Action Console, followed by a "recent work" section pulling in three separate real projects. Services page: Four core offerings — Anomaly Detection Dashboards, Power BI & Data Analytics, AI-Integrated Internal Tools, and Custom Data Automation — each paired with an actual screenshot of that specific project (not a mockup). About page: A short, direct bio and a real photo, no filler. Contact page: A simple inquiry form paired with a data-visualization graphic that matches the site's overall theme. How I used Finish Layer Block Animations: I used on-appear and on-scroll triggers (Reveal and Slide styles) across the homepage, services, and contact pages. Section headings reveal as the page loads, and content blocks slide/fade in as the visitor scrolls — this turns what would be a static, all-at-once page into a guided, paced experience. Block Transform: Rather than a flat grid, I applied a subtle rotation to a couple of key visuals (a dashboard screenshot and the contact-page graphic) — just a few degrees, enough to break the rigidity of the layout without sacrificing readability. It gives the page an asymmetrical, more intentional feel instead of looking templated. Process I built this using Squarespace's Blueprint AI to get a fast base structure, then went through every page replacing AI-generated placeholder content (stock imagery, generic service descriptions, an accidental product/ecommerce section) with real project data, real screenshots, and copy that actually reflects how I work with clients. The site is password-protected rather than published on a paid plan, and is fully responsive across desktop and mobile. Access: 🔗 Site: https://pike-megalodon-4yb2.squarespace.com (https://pike-megalodon-4yb2.squarespace.com)🔑 Password: Omega

2

321

Cover image for Anomaly Review & Action Console (Retool + AI)

Anomaly Review & Action Console (Retool + AI)

1

6

Data Analyst & BI Dev | Dashboards, SQL, Python & ETL

New to Contra

Data Analyst & BI Dev | Dashboards, SQL, Python & ETL

Cover image for Marketplace Profitability & P&L Engine
Overview
This

Marketplace Profitability & P&L Engine Overview This project is an end-to-end E-commerce Marketplace Analytics solution built using MySQL, SQL, Power BI, and Excel. The objective of this project is to analyze marketplace profitability across multiple sales channels by calculating revenue, product costs, marketplace commissions, shipping expenses, and net profit. The project simulates a real-world marketplace operations environment where business teams need visibility into product performance, marketplace profitability, and operational KPIs. Business Problem E-commerce businesses often track revenue but fail to understand true profitability. This project helps answer key business questions: Which marketplace generates the highest profit? Which products are most profitable? How do commissions impact margins? What is the overall profit margin? How does shipping cost affect profitability? Tech Stack MySQL SQL Power BI Microsoft Excel Data Sources Products Contains SKU-level product information. Fields: SKU Product Name Category Cost Price Selling Price Orders Contains marketplace order transactions. Fields: Order ID Order Date Marketplace SKU Quantity Marketplace Charges Marketplace commission structure. Fields: Marketplace Commission Percentage Shipping Cost Shipping cost by marketplace. Fields: Marketplace Shipping Cost Returns Order return information. Fields: Order ID Return Status SQL Implementation The project uses multiple SQL tables and joins to create a unified profitability dataset. Key SQL Concepts Used: CREATE TABLE INNER JOIN SQL Views Aggregations Calculated Metrics A consolidated analytical view was created: vw_marketplace_pnl This view combines all business logic and serves as the primary source for Power BI reporting. Profitability Metrics Revenue Revenue = Quantity × Selling Price Product Cost Product Cost = Quantity × Cost Price Commission Cost Commission Cost = Revenue × Marketplace Commission % Shipping Cost Shipping Cost = Quantity × Shipping Cost Profit Profit = Revenue − Product Cost − Commission Cost − Shipping Cost Profit Margin % Profit Margin % = Profit / Revenue Power BI Dashboard Executive Summary KPIs: Total Revenue Total Profit Total Orders Profit Margin % Marketplace Analysis Revenue by Marketplace Profit by Marketplace Marketplace Performance Comparison Product Analysis Top Profitable Products Product Revenue Analysis Product Profitability Ranking Trend Analysis Revenue Trend Profit Trend Order Trend Project Architecture Excel → MySQL → SQL View → Power BI Dashboard Key Outcomes Built a scalable marketplace profitability model. Centralized business logic using SQL Views. Automated profitability calculations. Delivered interactive executive dashboards for decision-making. Simulated a real-world marketplace operations analytics workflow. Skills Demonstrated SQL Data Modeling Business Intelligence Power BI E-commerce Analytics Marketplace Operations Profitability Analysis Data Visualization Author Sunny Mehta Open to opportunities in: E-commerce Operations Marketplace Management Business Analytics Operations Analytics Data Analytics

0

15

Cover image for Netflix Movies Analysis Dashboard using

Netflix Movies Analysis Dashboard using Power BI Project Overview Interactive Power BI dashboard analyzing Netflix movie trends, popularity, ratings, genres, and language distribution. KPIs Total Movies Total Votes Total Popularity Average Rating Dashboard Features Top 10 Movies by Popularity Release Year Trend Movies Distribution by Language Genre Analysis Popularity vs Vote Average Tools Used Power BI Power Query DAX Data Modeling

3

79

Cover image for Banking Data Analysis Dashboard

Develop a

Banking Data Analysis Dashboard Develop a basic understanding of risk analytics in banking and financial services and understand how data is used to minimise the risk of losing money while lending to customers Solution – With our dashboards which are created using Power BI latest tools helps the company to make a decision based on the applicant’s profile like if the applicant is likely to repay the loan then approving the loan otherwise not. About Dataset – This dataset basically contains information about bank details ,various client details which consists of multiple tables which are interlinked with each other through keys like primary key and foreign key. The various tables are Banking Relationship, Client-Banking, Gender, Investment Advisor and Period. KPI’S: In which followings KPIS are present : Total Clients : Total Clients KPI represents total number of clients in banking. Total Clients = DISTINCTCOUNT('Clients - Banking'[Client ID] ) Total Loan : Total Loan gives you information about the bank loan + Business lending + credit cards balance of particular investor , gender. Total Loan = [Bank Loan] + [Business Lending] + [Credit Cards Balance] Bank Loan : Bank Loan gives you information what is the loan amount of loan to be repaid by the client to bank. Bank Loan = SUM('Clients - Banking'[Bank Loans] ) Business Lending : Business lending gives you information about the loan amount given to small business. Business Lending = SUM('Clients - Banking'[Business Lending] ) Total Deposit Total Deposit gives you information about the amount deposited by particular investors in bank Total Deposit = [Bank Deposit] + [Savings Account] + [Foreign Currency Account] + [Checking Accounts] Total Fees : Total Fees is nothing but the amount charged by the bank for account set-up , maintenance charges etc. Total Fees = SUMX('Clients - Banking' , [Total Loan] * 'Clients - Banking'[Processing Fees] ) Bank Deposit : Bank deposit is the money put in the bank. Bank Deposit = SUM('Clients - Banking'[Bank Deposits] ) Checking Account Amount : Checking account amount is nothing but which offers easy access to your money for daily transactional needs. Checking Accounts = SUM('Clients - Banking'[Checking Accounts] ) Total CC Amount : Total CC Amount is a short-term source of financing for a company by a bank. Total CC Amount = SUM('Clients - Banking'[Amount of Credit Cards] ) Saving Account Amount : A savings account is an interest-bearing deposit account held at a bank. Savings Account = SUM('Clients - Banking'[Saving Accounts] ) Foreign Currency Amount : Foreign Currency Account means an account held in a currency that is not the currency of India or Bhutan or Nepal. Foreign Currency Account = SUM('Clients - Banking'[Foreign Currency Account] ) Engagement Account : Engagement Banking is nothing but puts the customer at the center and aims to deliver the digital experiences they expect. Engagment Length = SUM('Clients - Banking'[Engagment Days]) Credit Cards Balance : It is the total amount of money currently owned by a cardholder to their credit card bank. Credit Cards Balance = SUM('Clients - Banking'[Credit Card Balance] ) 📊 Tools Used Excel (Data Cleaning) SQL (Data Processing) Python (EDA) Power BI (Dashboard) 📈 Key Insights Private banks dominate loan distribution European segment shows highest deposits Low-income customers have high loan dependency

1

47

Cover image for Blinkit-Sales-Dashboard
This project is an interactive

Blinkit-Sales-Dashboard This project is an interactive Power BI dashboard developed to analyse Blinkit's sales performance, outlet operations, product distribution, and customer-related metrics. The dashboard converts raw retail sales data into meaningful business insights through visualisation and KPI tracking. The objective of this project is to monitor business performance, identify sales trends, evaluate outlet efficiency, and support data-driven decision-making. Key KPIs Total Sales: $1.20M Average Sales: $140.99 Number of Items: 8,523 Average Rating: 3.9 Dashboard Features Sales Analysis Tracked total revenue and average sales performance to understand overall business growth. Outlet Performance Analysed outlet sales based on the following: Outlet Size Outlet Location Type Outlet Establishment Year Outlet Type Product Category Analysis Identified top-performing product categories contributing the highest revenue. Customer & Product Insights Compared low-fat and regular products to understand purchasing trends and monitored customer ratings for performance evaluation. Interactive Filters Added slicers for: Outlet Location Type Outlet Size Item Type Outlet Type Outlet Identifier These filters allow users to dynamically explore data and generate business insights. Project Outcome This project demonstrates practical skills in business intelligence, KPI reporting, analytical thinking, and dashboard development using Power BI. It highlights the ability to transform raw business data into business insights for decision-making. Developed By Sunny Mehta

1

59

Expert Data Analyst & Machine Learning Specialist | Python

Expert Data Analyst & Machine Learning Specialist | Python

Cover image for E-Commerce Reverse Logistics Analysis and Prediction

E-Commerce Reverse Logistics Analysis and Prediction

0

7

Cover image for Online Retail Price Analysis - Flipkart vs Amazon

Online Retail Price Analysis - Flipkart vs Amazon

0

5

Cover image for Flipkart Laptop Web Scraping Project

Flipkart Laptop Web Scraping Project

0

5

Placeholder project card media

View more →

Sawantwadi, India

Backend Developer, AI Agent Builder, ML Engineer, Python Dev

Backend Developer, AI Agent Builder, ML Engineer, Python Dev

Cover image for Conditional GAN for MNIST with Linear Architecture

Conditional GAN for MNIST with Linear Architecture

1

8

Cover image for Simple GPT-2 Implementation with PyTorch Lightning

Simple GPT-2 Implementation with PyTorch Lightning

1

3

Cover image for AI Quiz Generator Web Application

AI Quiz Generator Web Application

1

7

Placeholder project card media

View more →

Tanish Khandelwal

Data Guru. AI Solutions. ML Engineer.

Data Guru. AI Solutions. ML Engineer.

Cover image for tknishh/payclosur

tknishh/payclosur

0

17

Cover image for tknishh/uber-mage-data-analysis

tknishh/uber-mage-data-analysis

0

34

Cover image for tknishh/FileWise

tknishh/FileWise

0

17

Placeholder project card media

View more →

TechAPeek Services

🔍 Transforming Data into Business Insights

🔍 Transforming Data into Business Insights

Cover image for Dynamic Advertisement Overlay

Dynamic Advertisement Overlay

0

13

Cover image for Billing Management System

Billing Management System

0

7

Cover image for HUMOUR DETECTION USING NLP

HUMOUR DETECTION USING NLP

0

76

Placeholder project card media

View more →

Kaustubh Bhiwsankar

Data Analytics Professional

Data Analytics Professional

Cover image for Geospatial Analysis and Feature Extraction 📊🌏

Geospatial Analysis and Feature Extraction 📊🌏

0

15

Cover image for Dynamic Media Scraping Solution 🎭

Dynamic Media Scraping Solution 🎭

0

8

Cover image for
End-to-End Data Analytics 📊💻🔍

End-to-End Data Analytics 📊💻🔍

0

12

Placeholder project card media

View more →