google-trends-ath-detector

To detect All-Time Highs and anomalies in Google Trends time series data, you can use a Selenium-based crawler to fetch topic data by region and apply signal typing to classify spikes. This approach outputs a structured JSON report for analysis.

Signal typing in Google Trends anomaly detection classifies time series spikes into three categories: seasonal spikes, event-driven shocks, or regime shifts. It extracts related queries to illuminate the underlying drivers of the detected anomaly.

You can compare multiple topics in Google Trends by fetching time series data for each topic and analyzing their resonance. This multi-topic comparison helps assess whether a detected anomaly represents systemic risk or an isolated event.

Yes, you need Selenium, webdriver-manager, BeautifulSoup4, and lxml to scrape Google Trends time series data. These dependencies drive the browser-based crawler and parse the HTML required for anomaly detection and signal typing.

Yes, you can extract related queries from Google Trends alongside time series anomaly detection. The crawled data is processed to illuminate the drivers behind seasonal spikes, event-driven shocks, and regime shifts in the structured JSON payload.

Selenium-based Google Trends crawling requires Python 3.8 or higher. This environment supports the necessary webdriver-manager, BeautifulSoup4, and lxml dependencies to execute the anomaly detection scripts and output valid JSON.