Sidak Vasu

INTERN

Indian Institute of Management RohtakRohtak, haryanafull_time, internship

Open to roles

Finance

Honk Hackathon

Urban commuters face daily uncertainty due to unreliable public transport schedules. Priya leaves home expecting an 8:22 bus, but inconsistent arrivals force her to either wait unnecessarily or miss her ride entirely. Existing map and transit apps often rely on outdated data and provide limited real-time visibility. The challenge is to build a lightweight, coding-first solution that delivers accurate live ETAs, delay predictions, and actionable commute recommendations, enabling users to make informed travel decisions in real time. Process We developed a lightweight real-time commute intelligence platform that aggregates live GPS feeds, transit APIs, and simulated vehicle telemetry streams. The backend processes incoming location updates through a prediction engine that analyzes route history, traffic conditions, and vehicle movement patterns to estimate arrival times. A machine learning layer continuously adjusts ETAs based on recent deviations, improving reliability over static schedules. The system delivers actionable insights such as bus arrival predictions, delay alerts, and alternate route suggestions. To maximize accessibility, the solution is optimized for low-bandwidth environments and can be accessed through a web interface, mobile devices, and WhatsApp-based interactions. Results The solution provides commuters with accurate, real-time transport information instead of static schedules. Users receive live ETAs, delay notifications, confidence scores, and alternative travel options, reducing uncertainty and unnecessary waiting time. Testing across simulated commute scenarios demonstrated significantly improved arrival predictions compared to fixed timetable-based systems. The lightweight architecture ensures fast performance even on low-end devices and limited internet connections, making the platform practical for everyday commuters and scalable across different cities Reflection With additional development time, I would expand the platform through larger-scale real-world GPS integrations and partnerships with transit operators to improve prediction accuracy. I would also implement crowd-sourced validation, allowing commuters to contribute live updates that strengthen the prediction engine. Further enhancements would include multilingual support, offline caching for intermittent connectivity, personalized commute recommendations based on user behavior, and a reinforcement learning model that continuously optimizes ETA accuracy as more transportation data becomes availa

7 media files · honkai-demo-lypttkmj.manus.spaceView

ipl crunch3

Standard IPL analysis relies on batting averages, economy rates, and strike r built for Test cricket that measure volume, not context. They cannot distinguish a match-winning 40 under extreme pressure from a comfortable 40 in a dead rubber. Franchise auction rooms misprice players because no tool quantifies clutch performance, phase-specific impact, or momentum collapse. Toss analysis is reported as a single aggregate, hiding dramatic venue-specific variation. The result: analysts describe what happened, never why and franchises make million-dollar decisions on the wrong number Process Ingested and merged 548K+ ball-by-ball deliveries across 16 IPL seasons from Cricsheet Cleaned and standardised franchise name changes, removed Super Overs, flagged rain-affected matches Engineered 7 custom cricket metrics from scratch unavailable in standard cricket databases Built over-level aggregations for phase-wise (PP / Middle / Death) win-factor analysis Trained and compared three ML models with out-of-time validation on held-out seasons Applied SHAP explainability to quantify which features drive win probability predictions Delivered an interactive HTML dashboard, complete Python pipeline, and plain-English report Results Death overs economy is the #1 match-outcome predictor — stronger than powerplay or wickets Toss advantage is 52.4% overall but climbs to 64% at dew venues and drops to 50% at three grounds 34% of PoM awards misidentify the true match-winner by Clutch Performance Index High boundary dependency teams lose more close matches than singles-focused teams Gradient Boosting model achieved AUC 0.79, accuracy 72% on out-of-time validation Go beyond standard cricket stats and build metrics with real franchise decision-making value Reflection 7 custom metrics built from first principles — Pressure Index, CPI, CSI, DOE, PAR, MSS, EUP — none exist in standard cricket data products Out-of-time model validation (train 2008–2021, test 2022–2024) instead of random splits — far more credible for sports data Toss analysis disaggregated by venue, not reported as a single number — revealed the myth hiding inside the average PoM award accuracy tested against CPI — exposed a structural bias in traditional cricket recognition Boundary dependency framed as a vulnerability, not an asset — counterintuitive finding backed by close-match win rate da

5 media files · iplanalytics-fus7wsg7.manus.spaceView

This is Sidak’s work on Wooble.

Build a profile that shows what you can do — and share it anywhere.

Build yours