Gold rose to 4,533.64 USD/t.oz on March 27, 2026, up 3.51% from the previous day. Over the past month, Gold's price has fallen 14.82%, but it is still 46.99% higher than a year ago, according to trading on a contract for difference (CFD) that tracks the benchmark market for this commodity. Gold - values, historical data, forecasts and news - updated on March of 2026.

Dataset Card for Sentiment Analysis of Commodity News (Gold)

This is a news dataset for the commodity market which has been manually annotated for 10,000+ news headlines across multiple dimensions into various classes. The dataset has been sampled from a period of 20+ years (2000-2021). The dataset was curated by Ankur Sinha and Tanmay Khandait and is detailed in their paper "Impact of News on the Commodity Market: Dataset and Results." It is currently published by the authors on… See the full description on the dataset page: https://huggingface.co/datasets/SaguaroCapital/sentiment-analysis-in-commodity-market-gold.

Gold is a primary global commodity used as a hedge against inflation and currency devaluation. This dataset combines long-term historical benchmarks from the World Bank with recent high-frequency market data to provide a continuous view of gold prices from 1995 through early 2026.

Content

The dataset consists of a single CSV file containing:

Date: The timestamp for the observation (Daily or Monthly).

Gold_Price_USD_YF: Market closing price in USD (via Yahoo Finance).

Gold_Price_WB_Monthly: Global benchmark price per troy ounce (via World Bank).

Data Sources

World Bank (wbdata): Historical global commodity "Pink Sheet" data.

Yahoo Finance (yfinance): Daily market spot and futures prices (Ticker: GC=F). https://finance.yahoo.com/quote/GC=F/history/

License

Data Files (CC BY 4.0): You are free to share and adapt this data as long as credit is given to the original sources (World Bank and Yahoo Finance).

Column Metadata

Assigning descriptions to individual columns is critical for a 10.0 usability score. | Column Name | Description | | :--- | :--- | | Date | The date of record in YYYY-MM-DD format. | | Gold_Price_USD_YF | The daily/monthly average closing price of Gold Futures in USD. | | Gold_Price_WB_Monthly | The monthly global average price of gold per troy ounce (World Bank benchmark). |

Dataset Citations:

World Bank (Primary source for 1995-2000): https://www.worldbank.org/en/research/commodity-markets

Yahoo Finance (Primary source for 2000-2026): https://finance.yahoo.com/quote/GC=F/history

Eurostat (Economic Indicators): https://ec.europa.eu/eurostat/data/database

FAOSTAT (Price Indices): https://www.fao.org/faostat/en/#data/PP

Keywords & Tags:

Finance, Commodities, Economics, Time Series Analysis, Global, Gold Prices, Historical Gold Prices, Monthly Gold Prices, World Bank, Yahoo Finance

Gold prices in , February, 2026 For that commodity indicator, we provide data from January 1960 to February 2026. The average value during that period was 635.09 USD per troy ounce with a minimum of 34.94 USD per troy ounce in January 1970 and a maximum of 5019.97 USD per troy ounce in February 2026. | TheGlobalEconomy.com

Graph and download economic data for Producer Price Index by Commodity: Metals and Metal Products: Gold Ores (WPU102105) from Jun 1985 to Dec 2021 about ore, gold, metals, commodities, PPI, inflation, price index, indexes, price, and USA.

Context

This is a news dataset for the commodity market where we have manually annotated 10,000+ news headlines across multiple dimensions into various classes. The dataset has been sampled from a period of 20+ years (2000-2021).

Content

The dataset has been collected from various news sources and annotated by three human annotators who were subject experts. Each news headline was evaluated on various dimensions, for instance - if a headline is a price related news then what is the direction of price movements it is talking about; whether the news headline is talking about the past or future; whether the news item is talking about asset comparison; etc.

Acknowledgements

Sinha, Ankur, and Tanmay Khandait. "Impact of News on the Commodity Market: Dataset and Results." In Future of Information and Communication Conference, pp. 589-601. Springer, Cham, 2021.

https://arxiv.org/abs/2009.04202 Sinha, Ankur, and Tanmay Khandait. "Impact of News on the Commodity Market: Dataset and Results." arXiv preprint arXiv:2009.04202 (2020)

We would like to acknowledge the financial support provided by the India Gold Policy Centre (IGPC).

Inspiration

Commodity prices are known to be quite volatile. Machine learning models that understand the commodity news well, will be able to provide an additional input to the short-term and long-term price forecasting models. The dataset will also be useful in creating news-based indicators for commodities.

Apart from researchers and practitioners working in the area of news analytics for commodities, the dataset will also be useful for researchers looking to evaluate their models on classification problems in the context of text-analytics. Some of the classes in the dataset are highly imbalanced and may pose challenges to the machine learning algorithms.

The purpose of this study was to look at the cointegration, spillover impact, and lead-lag connection for returns across spot price and the futures price of products gold and silver. Everyday spot and futures prices of Gold and Silver, which were heavily exchanged on the Multi Commodity Exchange (MCX) throughout 2019-2020, were used to compile the data for this study. The return series are considered for testing the spillover effect between the series through GARCH (1,1) Model. The series are checked for stationarity before using the GARCH (1,1) model. The ADF (Augmented Dickey Fuller) test was used to examine the return series' stationarity. The Johansen cointegration and Granger causality tests were used to validating the cointegration and lead-lag connection between futures and spot pricing for chosen bullion commodities after the return series was confirmed stationary. The analysis helps to achieve the following Hypotheses: H01: There is no stationarity in the dataset for the chosen bullion commodities. H02: Cointegration between futures and spot prices is not present in the market for the chosen bullion commodities. H03: The futures price is not influenced by the spot price for the chosen bullion commodities. H04: The Spot price is not influenced by the Futures price for the chosen bullion commodities

The finding provides a new view of the series cointegration, lead-lag, and spillover effect. The spot and futures prices of gold and silver are considered for price discovery. It tells derivatives traders that gold and silver are preferable assets for hedgers and speculators to diversify their portfolios.

This dataset can be used to predict the stock market. The data is extracted from MT5 terminal integrated in python.

The datasets include the minute by minute fluctuations of Gold and Silver prices over from 1st of January 2023 to 17th April 2025. The data can be used to train models for seasonality or a minute-by-minute approach.

The data has 7 columns:

• Time: The minute in which the event or movement occurred (Can be converted to Datetype with pd.to_datatime)
• Open Price
• High Price
• Low Price
• Close Price (The Feature to Predict if desired)
• Tick Volume: The Volume at the in which the event or movement occurred
• EMA: Exponential Moving Average (Technical Estimator for Risk management in the predictions and overall better performance)
• OBV: On-Balance Volume (Technical Estimator for Risk management in the predictions and overall better performance)

Two datasets are used;

Achilles Data Gold-Silver: with 1,416,340 rows to predict Gold, Silver and other Metals. Achilles Data Gold: with 708,264 rows to predict Gold, Silver and other Metals.

You may find the paper of our implementation here: https://doi.org/10.48550/arXiv.2410.21291

This Dataset contains Historical Price of Gold in Indian Commodity Market . The data has been collected from https://in.investing.com/commodities/ using web scrapping . The script can be customized to suit the needs (like customizing frequency interval , commodity type etc ) Link to web scrapping script - https://github.com/Pritam3355/web_scrapping/blob/master/stock_price.py

Column contains - Date, Price ,Open , High ,Low ,Volume ,Chg% these columns can be sorted first in the website then use the url in script to download the data according to your need

View monthly updates and historical trends for All Commodities Excluding Gold Price Index. Source: International Monetary Fund. Track economic data with Y…

In 2024, the rate of return on gold was 26.62 percent, making gold the leading commodity based on return rate in that year. Natural resources, like any other investment, exhibit a wide range of fluctuations over time.

This data release contains the U.S. salient statistics and world production data extracted from the GOLD data sheet of the USGS Mineral Commodity Summaries 2024.

Germany Commodity Price: Precious Metals: Gold data was reported at 4,474.096 USD/Troy oz in 24 Mar 2026. This records an increase from the previous number of 4,407.857 USD/Troy oz for 23 Mar 2026. Germany Commodity Price: Precious Metals: Gold data is updated daily, averaging 1,506.784 USD/Troy oz from Jan 2013 (Median) to 24 Mar 2026, with 3353 observations. The data reached an all-time high of 5,393.867 USD/Troy oz in 29 Jan 2026 and a record low of 1,050.717 USD/Troy oz in 17 Dec 2015. Germany Commodity Price: Precious Metals: Gold data remains active status in CEIC and is reported by Deutsche Börse Group. The data is categorized under Global Database’s Germany – Table DE.P: Commodity Prices. [COVID-19-IMPACT]

As of December 1st, 2025, gold futures contracts to be settled in June 2031 were trading on U.S. markets at around ***** U.S. dollars per troy ounce. This is above the price of ******* U.S. dollars per troy ounce for contracts to be settled in December 2025, indicating that gold traders expect the price of gold to rise over the next five years. Gold futures are contracts that effectively lock in a price for an amount of gold to be purchased at a time in the future, which can then be traded on markets. Futures markets therefore provide an indicator of how investors think a commodities market will develop in the future.

This data release contains the U.S. salient statistics and world production data extracted from the GOLD data sheet of the USGS Mineral Commodity Summaries 2022.

This comprehensive dataset contains 10 years of historical gold futures prices (2016-2026) sourced from Yahoo Finance, along with advanced machine learning predictions extending through December 2026. Perfect for financial analysis, time series forecasting, and machine learning enthusiasts.

Keywords: gold price prediction, time series forecasting, XGBoost, financial analysis, commodity trading, investment analysis, machine learning finance, gold futures, technical analysis, price forecasting

Historical Data Columns:** - Date (index) - Open, High, Low, Close prices (USD) - Volume - Adjusted Close Machine Learning Projects - Time series forecasting - Regression modeling - Feature engineering practice - Model comparison studies

✅ Financial Analysis - Investment strategy backtesting - Risk assessment - Trend analysis - Portfolio optimization

✅ Educational Purposes - Learning technical analysis - Understanding commodity markets - Practicing data visualization - Exploring EDA techniques

Model Performance

🤖 XGBoost Regression Model: - R² Score: 0.99+ (99%+ variance explained) - MAPE: <1% (prediction error) - RMSE: ~$15-20 (typical error range) - Training Set: 2,000+ samples - Test Set: 500+ samples

Data Source & Citation

Primary Source: Yahoo Finance (yfinance Python API) Ticker Symbol: GC=F (Gold Futures - COMEX) API: https://pypi.org/project/yfinance/ License: Educational and research purposes

This data release contains the U.S. salient statistics and world production data extracted from the GOLD data sheet of the USGS Mineral Commodity Summaries 2025.

United States - Producer Price Index by Commodity: Metals and Metal Products: Gold Ores was 444.72200 Index Jun 1985=100 in December of 2021, according to the United States Federal Reserve. Historically, United States - Producer Price Index by Commodity: Metals and Metal Products: Gold Ores reached a record high of 515.90000 in August of 2020 and a record low of 78.40000 in April of 2001. Trading Economics provides the current actual value, an historical data chart and related indicators for United States - Producer Price Index by Commodity: Metals and Metal Products: Gold Ores - last updated from the United States Federal Reserve on March of 2026.

This data release contains the U.S. salient statistics and world production data extracted from the GOLD data sheet of the USGS Mineral Commodity Summaries 2023.

Context

Gold. A precious item with its own duality. In one side, it's a popular investment asset. In another side, it's a commodity. Whether you buy it as an asset or as commodity, the price for gold is always influenced by two things, as similar as other commodities in market: supply and demand. It's not easy to combine many aspects in supply and demand into a single dataset without making it into wall of columns. And also aggregating the data might not easy to do, since the data might not available publicly. But it doesn't mean we can't learn the historical pattern of gold market. At least some gold price historical data are available for public. And we can use that to analyze the market pattern, and, maybe, learn something from them.

Content

This dataset was based on gold price historical data from macrotrends.net. I added one new column, 'Year Range Price', to see how wide the spread of the price annually.

Acknowledgements

The base data for this dataset was retrieved from https://www.macrotrends.net/1333/historical-gold-prices-100-year-chart.

Inspiration

What variable have the biggest correlation with annual Average Closing Price? What information can we see from the graphic? Are there any reasons why the price drop and rise? What happened on those years? Many things can be learn and explore by historical data. Having historical data is like having a kaleidoscope to see the past, learn from them, and use it as information to walk on our future path.