Dataset of historical annual gold prices from 1970 to 2024, including significant events and acts that impacted gold prices.

Gold fell to 4,199.97 USD/t.oz on December 2, 2025, down 0.75% from the previous day. Over the past month, Gold's price has risen 4.93%, and is up 58.92% compared to the same time last year, 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 December of 2025.

Gold Prices - Historical chart and current data through 2025.

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F19238395%2F16f18b685654bc1f07d8d614bcea2e13%2FScreenshot%202024-06-25%20141846.png?generation=1719305359168334&alt=media" alt="">

Gold Price Prediction in INR (2004-2024)🇮🇳 - Can You Forecast the Future? ✨

Data Description:

1. Time Period: October 2004 - December 2024 (20 years) - Long-term Trend Analysis!
2. Frequency: Monthly Average Gold Price (INR) - Uncover Seasonality!
3. Source: Financial Service Website (verified) ✅ - Reliable Data for Accurate Predictions!

Potential Applications:

• Time Series Analysis: Analyze trends and seasonality in gold prices. - Unravel the Gold Market Mystery! ️‍♀️
• Gold Price Prediction: Forecast future gold prices using ARIMA, SARIMA, fbProphet, etc. - Predict the Next Big Move!

Key Points:

• Long-Term Trend: Explore the evolution of gold prices over two decades. - See How Gold Has Changed Over Time! ⏳
• Prediction Models: Evaluate the effectiveness of different time series forecasting models. - Find the Best Tool for the Job!
• INR Focus: Gain insights specific to the Indian gold market. 🇮🇳 - Understand the Indian Gold Market Landscape! ️

⚠️ Note:

• Past performance does not guarantee future results.

Bonus:

This dataset allows you to explore the fascinating world of gold price prediction in the Indian market. Challenge yourself! Can you develop a model that outperforms the rest?

This statistic depicts the average annual prices for gold from 2014 to 2024 with a forecast until 2026. In 2024, the average price for gold stood at 2,388 U.S. dollars per troy ounce, the highest value recorded throughout the period considered. In 2026, the average gold price is expected to increase, reaching 3,200 U.S. dollars per troy ounce.

Monthly and long-term gold price data (US$/toz): historical series and analyst forecasts curated by FocusEconomics.

The price of gold per troy ounce increased considerably between 1990 and 2025, despite some fluctuations. A troy ounce is the international common unit of weight used for precious metals and is approximately **** grams. At the end of 2024, a troy ounce of gold cost ******* U.S. dollars. As of * June 2025, it increased considerably to ******** U.S. dollars. Price of – additional information In 2000, the price of gold was at its lowest since 1990, with a troy ounce of gold costing ***** U.S. dollars in that year. Since then, gold prices have been rising and after the economic crisis of 2008, the price of gold rose at higher rates than ever before as the market began to see gold as an increasingly good investment. History has shown, gold is seen as a good investment in times of uncertainty because it can or is thought to function as a good store of value against a declining currency as well as providing protection against inflation. However, unlike other commodities, once gold is mined it does not get used up like other commodities (for example, such as gasoline). So while gold may be a good investment at times, the supply demand argument does not apply to gold. Nonetheless, the demand for gold has been mostly consistent.

Context

Gold is one of the world's most closely watched commodities, serving as a key indicator of economic health, a hedge against inflation, and a cornerstone of financial markets. Access to clean, reliable, and long-term historical data is essential for analysts, investors, and data scientists looking to understand its behavior, forecast future trends, and build robust financial models.

This dataset provides a comprehensive and daily-updated record of gold prices, specifically sourced from the Gold Futures (GC=F) market, which is the standard for long-term historical analysis.

Content

This dataset contains daily price information for Gold Futures (GC=F) in a clean, tabular format. Each row represents a single trading day and includes the following columns:

Date: The date of the trading session (YYYY-MM-DD).

Open: The price at which gold first traded for the day in USD.

High: The highest price reached during the trading day in USD.

Low: The lowest price reached during the trading day in USD.

Close: The closing price at the end of the trading day in USD.

Volume: The total number of futures contracts traded during the day.

Between January 1971 and May 2025, gold had average annual returns of **** percent, which was only slightly more than the return of commodities, with an annual average of around eight percent. The annual return of gold was over ** percent in 2024. What is the total global demand for gold? The global demand for gold remains robust owing to its historical importance, financial stability, and cultural appeal. During economic uncertainty, investors look for a safe haven, while emerging markets fuel jewelry demand. A distinct contrast transpired during COVID-19, when the global demand for gold experienced a sharp decline in 2020 owing to a reduction in consumer spending. However, the subsequent years saw an increase in demand for the precious metal. How much gold is produced worldwide? The production of gold depends mainly on geological formations, market demand, and the cost of production. These factors have a significant impact on the discovery, extraction, and economic viability of gold mining operations worldwide. In 2024, the worldwide production of gold was expected to reach *** million ounces, and it is anticipated that the rate of growth will increase as exploration technologies improve, gold prices rise, and mining practices improve.

This dataset provides a comprehensive overview of currency values across USD, EUR, GBP, INR, AED, and CNY from 2001 to 2024. It showcases a general upward trend in values, reflecting global economic growth interspersed with periods of fluctuation. The USD, EUR, and GBP have shown relatively steady growth, with major leaps around 2006 and 2020, likely mirroring the impact of significant economic events such as the 2008 financial crisis and the COVID-19 pandemic. The sharp increases in 2020 and subsequent years suggest economic disruptions and recoveries tied to global health and economic challenges.

The dataset also highlights distinct economic dynamics in emerging and developed markets. For instance, the Indian Rupee (INR) and the Chinese Yuan (CNY) show significant long-term increases, indicating robust economic expansion in these regions. Meanwhile, more developed currencies, like the AED, exhibit consistent but less volatile growth patterns, reflective of their established economic stability. The data set's year-over-year progression offers a valuable lens for examining economic resilience, currency depreciation, and overall market trends, which are critical for analysts, investors, and policymakers in financial and economic planning.

Prices of Bitcoin, US stock indices, Gold and crude oil

Context

Real time prices in the diamond market are reflected by the so-called Diamond Financial Index (DFX) which is available on a daily base since April 2018.

As diamond prices are influenced by many factors like trade barriers, political instability, operational disruptions like mine closures or economic downturns resp. upturns, it is not an easy task to predict the development of future diamond prices.

To predict prices, indicators are needed. Empirical findings support the argument that diamond prices respond to economic downturns resp. upturns and are therefore also correlated with inflation rates and interest rates resp. fed rates. Also gold prices could be an indicator for the development of diamond prices.

Because the US are playing quite a big role in the diamond business, the following US rates can be considered:

o inflation rate (10-year breakeven inflation rate) o interest rate (10-year treasury inflation-indexed security, constant maturity, risk-free) o fed rate (effective federal funds rate)

Moreover, gold prices could be considered as an indicator.

Content

The following five datasets have been downloaded from the following websites and merged to one dataset:

o diamond price (DFX): https://www.investing.com/indices/get-diamonds-general o inflation rate: https://fred.stlouisfed.org/series/T10YIE o interest rate: https://fred.stlouisfed.org/series/DFII10 o fed rate: https://fred.stlouisfed.org/series/DFF o gold price: https://www.boerse-online.de/rohstoffe/historisch/goldpreis/usd/

To merge the datasets, date has been used as index. A few missing values in the datasets have been filled in by copying the value from the day before (see file "diamond_data_merged_with_other_variables.csv").

Please note: I added one additional version of the dataset where ID is used as index (not date). Missing values are not filled in in this version (see file "df_diamond_data_merged_with_other_variables.csv"). I would recommend using the dataset "diamond_data_merged_with_other_variables.csv" with date as index.

Inspiration

The following questions could be answered:

o How did diamond prices, inflation rate, interest rate, fed rate and gold price develop since 2018? o How is the correlation between diamond prices and inflation rate, interest rate, fed rate and gold prices? o How will diamond prices develop in the future?

When it comes to price prediction machine learning has been successful in predicting stock market prices through a host of different time series models. There is also a limited but quite restrictive application in predicting cryptocurrency prices. Often neural networks like LSTM (Long Short Term Memory) are used. LSTM oder other models, e.g. ARIMA, could be also used here.

Banking and stock markets consider gold to be an important component of their economic and financial status. There are various factors that influence the gold price trend and its fluctuations. Accurate and reliable prediction of the gold price is an essential part of financial and portfolio management. Moreover, it could provide insights about potential buy and sell points in order to prevent financial damages and reduce the risk of investment. In this paper, different architectures of deep neural network (DNN) have been proposed based on long short-term memory (LSTM) and convolutional-based neural networks (CNN) as a hybrid model, along with automatic parameter tuning to increase the accuracy, coefficient of determination, of the forecasting results. An illustrative dataset from the closing gold prices for 44 years, from 1978 to 2021, is provided to demonstrate the effectiveness and feasibility of this method. The grid search technique finds the optimal set of DNNs’ parameters. Furthermore, to assess the efficiency of DNN models, three statistical indices of RMSE, RMAE, and coefficient of determination (R2), were calculated for the test set. Results indicate that the proposed hybrid model (CNN-Bi-LSTM) outperforms other models in total bias, capturing extreme values and obtaining promising results. In this model, CNN is used to extract features of input dataset. Furthermore, Bi-LSTM uses CNN’s outputs to predict the daily closing gold price.

Official statistics, Data of scientific publications.

The size of the Gold Market was valued at USD 3.2 Trillion in 2023 and is projected to reach USD 4.5 Trillion by 2032, with an expected CAGR of 7.38% during the forecast period. Recent developments include: March 2023: Pan American Silver Corporation acquired all the issued and outstanding common shares of Yamana Gold Inc., as part of the arrangement, which includes its mines and increased the geographical operations of the company in Latin America., February 2023: Barrick Gold, the world's second-biggest gold producer, announced a 10% increase in attributable proved and probable gold mineral reserves to 76 million ounces net of depletion in 2022 while maintaining current reserves.. Key drivers for this market are: Demand for Gold in the form of Jewelry and Long-term Savings, Increasing Consumption in High-End Electronics Applications; Other Drivers. Potential restraints include: Declining Ore Grades and Other Technical Challenges, Other Restraints. Notable trends are: Jewelry Segment to Dominate the Demand.

Forecasting gold prices remains vital in financial markets, given gold’s dual role as both a hedge against inflation and a safe-haven asset during economic uncertainty. This study proposes a hybrid model integrating SARIMA, LSTM, and RF to improve predictive accuracy by capturing both linear and nonlinear dependencies in historical gold price data. SARIMA models linear trends and seasonal components, LSTM captures nonlinear patterns from SARIMA residuals, and RF refines predictions using macroeconomic indicators such as the USD Index, Federal Interest Rate, US CPI, Oil Prices, S&P 500 Index, and Bond Yields. Utilizing real-world data, the model effectively tracks market trends with reduced forecasting errors, indicating continued price fluctuations and potential long-term growth. The findings provide valuable insights for investors and policymakers, with future research focusing on additional macroeconomic factors and advanced hybrid forecasting techniques. This study introduces a hybrid SARIMA–LSTM–RF model that enhances the accuracy of gold price forecasting by capturing both linear and nonlinear market dynamics. By integrating macroeconomic indicators such as the USD Index, Federal Interest Rate, CPI, Oil Prices, S&P 500 Index, and Bond Yields, the model effectively reflects real-world financial interactions influencing gold prices. The results demonstrate reduced prediction errors and improved tracking of short-term fluctuations as well as long-term growth trends. These findings provide valuable implications for investors and policymakers in managing financial risk and optimizing investment portfolios, while contributing to the advancement of hybrid forecasting frameworks for complex financial time series.

Context

SPDR Gold Shares (GLD) This fund buys gold bullion. The only time it sells gold is to pay expenses and honor redemptions​. Because of the ownership of bullion, this fund is extremely sensitive to the price of gold and will follow gold price trends closely.

One upside to owning gold bars is that no one can loan or borrow them. Another upside is that each share of this fund represents more gold than shares in other funds that do not buy physical gold. However, the downside is taxes. The Internal Revenue Service (IRS) considers gold a collectible, and taxes on long-term gains are high. (For more, see: The Most Affordable Way to Buy Gold: Physical Gold or ETFs?)

Content

Fund overview: CategoryCommodities Precious Metals Fund familySPDR State Street Global Advisors

Acknowledgements

Yahoo Finance

Inspiration

Dataset will be helpful for people who are looking to start playing the Time Series Analysis. What always got my attention was, when Dollar goes down DowJones and Nasdaq goes up and vice-versa. Can this dataset be used for creating a Causal Model?

Banking and stock markets consider gold to be an important component of their economic and financial status. There are various factors that influence the gold price trend and its fluctuations. Accurate and reliable prediction of the gold price is an essential part of financial and portfolio management. Moreover, it could provide insights about potential buy and sell points in order to prevent financial damages and reduce the risk of investment. In this paper, different architectures of deep neural network (DNN) have been proposed based on long short-term memory (LSTM) and convolutional-based neural networks (CNN) as a hybrid model, along with automatic parameter tuning to increase the accuracy, coefficient of determination, of the forecasting results. An illustrative dataset from the closing gold prices for 44 years, from 1978 to 2021, is provided to demonstrate the effectiveness and feasibility of this method. The grid search technique finds the optimal set of DNNs’ parameters. Furthermore, to assess the efficiency of DNN models, three statistical indices of RMSE, RMAE, and coefficient of determination (R2), were calculated for the test set. Results indicate that the proposed hybrid model (CNN-Bi-LSTM) outperforms other models in total bias, capturing extreme values and obtaining promising results. In this model, CNN is used to extract features of input dataset. Furthermore, Bi-LSTM uses CNN’s outputs to predict the daily closing gold price.

Discover the latest trends and insights into the booming gold market, projected to reach $XX million by 2025 and grow at a 7.38% CAGR. This comprehensive analysis covers market drivers, restraints, regional breakdowns, and key players shaping this lucrative industry. Explore investment opportunities and future market prospects. Recent developments include: March 2023: Pan American Silver Corporation acquired all the issued and outstanding common shares of Yamana Gold Inc., as part of the arrangement, which includes its mines and increased the geographical operations of the company in Latin America., February 2023: Barrick Gold, the world's second-biggest gold producer, announced a 10% increase in attributable proved and probable gold mineral reserves to 76 million ounces net of depletion in 2022 while maintaining current reserves.. Key drivers for this market are: Demand for Gold in the form of Jewelry and Long-term Savings, Increasing Consumption in High-End Electronics Applications; Other Drivers. Potential restraints include: Demand for Gold in the form of Jewelry and Long-term Savings, Increasing Consumption in High-End Electronics Applications; Other Drivers. Notable trends are: Jewelry Segment to Dominate the Demand.

Context

As I am trying to learn and build an LSTM prediction model for equity prices, I have chosen gold price to begin.

Content

The file composed of simply 2 columns. One is the date (weekend) and the other is gold close price. The period is from 2015-01-04 to 2017-09-24.

Acknowledgements

Thanks to Jason of his tutorial about LSTM forecast: https://machinelearningmastery.com/time-series-forecasting-long-short-term-memory-network-python/

Inspiration

William Gann: Time is the most important factor in determining market movements and by studying past price records you will be able to prove to yourself history does repeat and by knowing the past you can tell the future. There is a definite relation between price and time.