Case Study · End-to-End Pipeline

Meditation Trend Pulse

An automated end-to-end data pipeline tracking global interest in meditation, mindfulness, and breathwork — from Google Trends ingestion to Prophet forecasting and a live multi-page Streamlit dashboard.

Streamlit Prophet Python PyTrends Pandas Automation Time Series Trend Analysis Google Trends

↗ Live App ⌥ GitHub Repo

3Dashboard Pages

9Cleaned Datasets

DailyAuto-Updates

ProphetForecasting Engine

Live App

Meditation Trend Pulse — Streamlit Community Cloud

↗ Open full screen

Loading app...

Streamlit's embedding policy may prevent inline display. Open the live app directly for the full interactive experience.

↗ Open Live App

⚡ Fully interactive — navigate pages using the sidebar · open full screen for best experience

The Problem

Meditation and mindfulness have gone mainstream — but which practices are actually growing, which are plateauing, and which are fading? Google Trends captures this signal in real time, but raw trend data is noisy, hard to interpret, and gone the moment you stop looking at it.

The goal was to build something that automatically collects, cleans, and stores Google Trends data daily — then surfaces it in a dashboard that answers real questions: Where in the world is mindfulness growing fastest? What's the forecast for breathwork over the next year? Which related queries are rising right now?

Approach

Automated Data Ingestion

Built a daily automation pipeline using PyTrends to pull Google Trends data for meditation, mindfulness, and breathwork. The script only overwrites datasets when fresh data is available — keeping the repo lightweight and reproducible.

PyTrendsAutomationPython ScriptsScheduling

EDA & Time Series Analysis

Cleaned and transformed 9 datasets covering global trends, country-level interest, and related queries. Applied smoothing, peak detection, percent change calculations, and monthly heatmaps to surface meaningful patterns in noisy trend data.

PandasNumPySmoothingPeak DetectionHeatmaps

Prophet Forecasting

Trained Facebook Prophet models on the cleaned time series to project future global search interest. Visuals surface uncertainty intervals and trend direction — giving the dashboard a predictive layer beyond descriptive stats.

ProphetTime SeriesForecastingUncertainty Intervals

Multi-Page Streamlit Dashboard

Built a 3-page Streamlit app with custom chakra-themed UI components, Altair charts, and a polished layout. Each page answers a distinct analytical question — global trends, country breakdowns, and related query analysis.

StreamlitAltairCustom UIMulti-page

Dashboard Pages

🌍

Global Trends

5-year search interest over time, smoothed trend lines, % change table, peak interest dates, and Prophet forecasts for each keyword.

🗺️

Country Trends

Top countries by practice, cross-keyword comparisons, share of global interest, and how different regions engage with each topic.

🔍

Related Queries

Top and rising search queries associated with each keyword — surfacing what people are actually searching alongside meditation and mindfulness, including shared interest signals across keywords.

Key Findings

Mindfulness consistently outperforms meditation and breathwork in global search interest over the 5-year window — but breathwork shows the steepest recent growth rate among the three.

Interest spikes reliably in January across all three keywords — driven by New Year wellness resolutions — making it the single most predictable peak in the annual cycle.

Country-level analysis reveals Australia, Canada, and the UK lead per-capita interest in mindfulness, while Southeast Asian countries show rising engagement with meditation specifically.

Prophet forecasts project continued moderate growth for all three keywords over the next 12 months, with widening uncertainty intervals — reflecting genuine ambiguity in post-pandemic wellness trends.

Related queries analysis surfaces "meditation for anxiety" and "breathwork techniques" as the fastest-rising associated searches — pointing to a shift from general interest to specific, need-driven queries.

Business Implication

This project demonstrates the full data engineering lifecycle — not just analysis. The automation layer means the dashboard stays current without manual intervention, which is the difference between a one-time analysis and a living data product.

For a wellness brand, content platform, or market research team, this pipeline could power content strategy, regional campaign targeting, and trend forecasting — all derived from a free public data source, refreshed daily, with no manual effort.