# The Proper Use of Google Trends in Forecasting Models

arXiv: https://arxiv.org/abs/2104.03065 · HTML: https://mlsanity.com/paper/2104.03065/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 24 references that are in the map.
- First posted on arXiv 7 Apr 2021.

## Builds on (most cited first, 2 of 2)

- [Short-Term Covid-19 Forecast for Latecomers](https://mlsanity.com/paper/2004.07977/) (2020)
- [Lockdown effects in US states: an artificial counterfactual approach](https://mlsanity.com/paper/2009.13484/) (2020)

## Built on by (most cited first, 3 of 3)

- [Well Googled is Half Done: Multimodal Forecasting of New Fashion Product Sales with Image-based Google Trends](https://mlsanity.com/paper/2109.09824/) (2021)
- [POP: Mining POtential Performance of new fashion products via webly cross-modal query expansion](https://mlsanity.com/paper/2207.11001/) (2022)
- [Forecasting Commencing Enrolments Under Data Sparsity: A Zero-Shot Time Series Foundation Models Framework for Higher Education Planning](https://mlsanity.com/paper/2602.12120/) (2026)

## Abstract (arXiv)

It is widely known that Google Trends have become one of the most popular free tools used by forecasters both in academics and in the private and public sectors. There are many papers, from several different fields, concluding that Google Trends improve forecasts' accuracy. However, what seems to be widely unknown, is that each sample of Google search data is different from the other, even if you set the same search term, data and location. This means that it is possible to find arbitrary conclusions merely by chance. This paper aims to show why and when it can become a problem and how to overcome this obstacle.