B.Sc
Data Science
Air Quality in Indian Metro Cities: An Analytics Study of CPCB Open Data (Python and Power BI)
From CPCB's open data to policy-ready dashboards for four metro cities
- Python
- pandas
- NumPy
- +3
Browse 310 projects
Three filters and a search box. Your guide's approval not included.
Filters
15 projects for “open-data” · sorted by most relevant
B.Sc
Data Science
Road Accident Fatalities across Indian States: An Applied Statistical Study of MoRTH Open Data
What five years of state-wise crash data say about where and why Indian roads kill — cleaned, tested and visualised
- Python
- pandas
- NumPy
- +5
M.ScCode included
Data Science
Groundwater Level Trend Analysis and Depletion Assessment for Tamil Nadu Districts (CGWB Open Data, Python)
Mann-Kendall trends, Sen's slopes and a depletion dashboard for CGWB observation wells, built entirely on open data
- Python 3 (pandas, NumPy, SciPy)
- pymannkendall (Mann-Kendall trend tests)
- statsmodels (SARIMA, Holt-Winters)
- +4
M.Tech / M.E.Code included
Civil Engineering
Machine-Learning Regression for Concrete Compressive Strength: Model Comparison and Mix Optimisation on Open Data
Linear, forest and boosting regressors compared by nested cross-validation; mixes proposed inside IS 456 constraints
- Python
- pandas
- NumPy
- +4
M.Sc
Data Science
Forecasting Tamil Nadu's Daily Peak Electricity Demand: SARIMA versus Gradient Boosting on Grid-India Data
An 11-year open-data dissertation on Tamil Nadu's daily peak demand, with weather covariates and honest walk-forward testing
- Python 3 (pandas, statsmodels, scikit-learn)
- R (Data Mining Lab coursework)
- Jupyter Notebook / R Markdown
- +3
M.Tech / M.E.
Data Science
BM25 vs Sentence-Embedding Retrieval on the data.gov.in Catalogue: A Significance-Tested Query-Level Evaluation
Graded-relevance, significance-tested comparison of sparse and dense retrieval on India's open-data catalogue
- Python
- pandas
- rank-bm25
- +5
M.ScCode included
Information Technology
A Data-Engineering Pipeline with Quality Monitoring for TRAI Crowdsourced Mobile-Speed Data
From monthly TRAI MySpeed downloads to a validated PostgreSQL warehouse and dashboard, with every number checked twice
- Python 3 (pandas, PyArrow)
- PostgreSQL 15 (warehouse)
- Apache Airflow (orchestration — industry-standard extra)
- +4
B.Tech / B.E.Code included
Data Science
MGNREGA Employment Analytics: ETL, Data Warehouse and Dashboard
A data-quality-gated pipeline from NREGA progress reports to a decision-ready warehouse and dashboard
- Python
- pandas
- MySQL
- +4
BCACode included
AI & Machine Learning
Bengaluru AQI Forecaster: Next-Day Air Quality Prediction from CPCB Station Data (Python, scikit-learn, Power BI)
Predict tomorrow's air quality band for every Bengaluru monitoring station, before the morning commute
- Python
- pandas
- scikit-learn
- +3
M.ScCode included
Information Technology
Linking School Infrastructure to Learning Outcomes: a UDISE+ and NAS District-Level Study
Two government datasets, one harmonised district table — does infrastructure actually move learning outcomes?
- Python 3 (pandas, NumPy)
- scikit-learn (regression diagnostics)
- statsmodels (OLS, correlation tests)
- +4
MCA
Data Science & Analytics
Dengue Outbreak Early-Warning and Surveillance Analytics System from NCVBDC Data (Python)
Turning NCVBDC surveillance counts and Open-Meteo climate reanalysis into a leak-free weekly dengue alert for city health teams
- Python 3.11
- pandas
- NumPy
- +5
B.Tech / B.E.Code included
Data Science
A Decade of UPI: Transaction Growth Analytics with SQL and Python
From NPCI's monthly tables to growth curves, seasonality and a trend forecast — one clean dataset, done properly
- Python
- pandas
- NumPy
- +4
M.Sc
Botany
Mapping Lantana camara Invasion in the Nilgiris: GBIF Occurrence Data and MaxEnt Habitat Modelling
Cleaned public occurrence records and WorldClim bioclimates turned into a habitat-suitability map for an invasive shrub
- GBIF.org occurrence downloads (with dataset DOIs)
- WorldClim 2.1 bioclimatic variables (30 arc-second rasters)
- MaxEnt 3.4 (maximum-entropy species distribution modelling)
- +3
BCACode included
AI & Machine Learning
Daily Outpatient Footfall Forecasting for a District Hospital OPD (Python, Keras, MySQL)
Forecast daily OPD crowds department by department, and plan the doctor roster before the Monday rush arrives
- Python
- pandas
- statsmodels
- +4
B.Sc
Computer Science
Route Planning on the Delhi Metro Network: A Benchmark Study of Shortest-Path Algorithms (Python)
Dijkstra, Bellman-Ford and A* measured on 243 real stations, not toy graphs
- Python
- NetworkX
- pandas
- +2