Natural gas rose to 4.94 USD/MMBtu on December 3, 2025, up 2.04% from the previous day. Over the past month, Natural gas's price has risen 13.71%, and is up 62.29% compared to the same time last year, according to trading on a contract for difference (CFD) that tracks the benchmark market for this commodity. Natural gas - values, historical data, forecasts and news - updated on December of 2025.

Crude Oil fell to 59.17 USD/Bbl on December 2, 2025, down 0.25% from the previous day. Over the past month, Crude Oil's price has fallen 3.08%, and is down 15.40% compared to the same time last year, according to trading on a contract for difference (CFD) that tracks the benchmark market for this commodity. Crude Oil - values, historical data, forecasts and news - updated on December of 2025.

Stock Price Time Series for YUNDA Holding Co Ltd. Yunda Holding Group Co., Ltd. provides express delivery services in China. The company offers express products; transshipment and other related services; data services; warehouse and distribution solutions for upstream and downstream customers; and collection, sorting, transfer, and delivery services. It also provides value-added services, including payment collection, insured business, store transfer, order return, reverse logistics, privacy bill, and scheduled delivery services. In addition, the company is involved in the sale of packaging materials, machinery, equipment, accessories, food, edible agricultural products, and petroleum products; investment management; cargo transportation and forwarding; online trade agent; internet, information, automation, and intelligent technology; technology development, transfer, and promotion; venture capital; technical, business, and information; business, information, financial, management, express, and enterprise management consulting; internet retail and agency; supply chain management; cargo freight and handling; e-commerce; house and non-residential real estate leasing; road transport of goods; advertising and marketing; art consulting and planning; property management; leasing of cars and equipment; manufacture of computer hardware and software; and smart device activities. Further, it engages in the wholesale and retail of medical equipment; online sale of daily necessities; commodity trading; leasing park management; engineering construction; business agency; software development; conference and exhibition; loading and unloading; wholesale of finished oil; import and export of goods and technologies; Internet of Things technology research and development; and network technology activities. The company was formerly known as YUNDA Holding Co., Ltd. and changed its name to Yunda Holding Group Co., Ltd. in November 2024. Yunda Holding Group Co., Ltd. was founded in 1996 and is based in Shanghai, China.

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.

Net-Receivables Time Series for Zheshang Development Group Co Ltd. Zhejiang Development Group Co.,Ltd engages in the commodity, financial leasing, online retailing, car sale and after service, and warehousing logistics service businesses in China and internationally. The company trades in screw-thread steel products, wire stocks, round steel products, hot rolled strips and coils, cold rolled products, I-beams, angle and groove bars, and steel feed and iron ore products; and provides value-added services, including wholesale and retail distribution, custom processing, warehouse delivery, financial services, e-commerce, logistics, etc., as well as upstream and downstream supply chain services. It also offers finance leasing, commercial factoring, and industrial bond and supply chain financing services; and industry management software products and services, customized development services for information management software products, software-as-a-service, and information technology management consulting services. In addition, the company provides supply chain integrated service, CRM, power sales management, financial leasing, car free carrier, unified enterprise mobile interconnected, enterprise integration, centralized purchasing management, logistics warehouse management, and cross-border e-commerce platforms, as well as commercial platform for commodities and data analysis platform for steel trade industry. Further, it offers warehousing, transportation, processing, logistics transaction, financial supervision, and other services. Additionally, the company sells and services cars of various brands through its 4S shops; and operates a taxi business. It operates approximately 8 standard 4S shops. The company was formerly known as Zhejiang Materials Development Co., Ltd. and changed its name to Zhejiang Development Group Co.,Ltd in January 2017. Zhejiang Development Group Co.,Ltd was founded in 1999 and is based in Hangzhou, China.

Depreciation Time Series for YUNDA Holding Co Ltd. Yunda Holding Group Co., Ltd. provides express delivery services in China. The company offers express products; transshipment and other related services; data services; warehouse and distribution solutions for upstream and downstream customers; and collection, sorting, transfer, and delivery services. It also provides value-added services, including payment collection, insured business, store transfer, order return, reverse logistics, privacy bill, and scheduled delivery services. In addition, the company is involved in the sale of packaging materials, machinery, equipment, accessories, food, edible agricultural products, and petroleum products; investment management; cargo transportation and forwarding; online trade agent; internet, information, automation, and intelligent technology; technology development, transfer, and promotion; venture capital; technical, business, and information; business, information, financial, management, express, and enterprise management consulting; internet retail and agency; supply chain management; cargo freight and handling; e-commerce; house and non-residential real estate leasing; road transport of goods; advertising and marketing; art consulting and planning; property management; leasing of cars and equipment; manufacture of computer hardware and software; and smart device activities. Further, it engages in the wholesale and retail of medical equipment; online sale of daily necessities; commodity trading; leasing park management; engineering construction; business agency; software development; conference and exhibition; loading and unloading; wholesale of finished oil; import and export of goods and technologies; Internet of Things technology research and development; and network technology activities. The company was formerly known as YUNDA Holding Co., Ltd. and changed its name to Yunda Holding Group Co., Ltd. in November 2024. Yunda Holding Group Co., Ltd. was founded in 1996 and is based in Shanghai, China.

Quickstart

https://colab.research.google.com/drive/1W6TprjcxOdXsNwswkpm_XX2U_xld9_zZ#offline=true&sandboxMode=true

Context

Predicting the stock market is a game as old as the stock market itself. On popular ML platforms like Kaggle, users often compete to come up with highly nuanced, optimized models to solve the stock market starting just from price data. LSTMs may end up being the most effective model, but the real problem isn't the model - it's the data.

Human and algorithmic traders in the financial industry know this, and augment their datasets with lots of useful information about stocks called "technical indicators". These indicators have fancy sounding names - e.g. the "Aroon Oscillator" and the "Chaikin Money Flow Index", but most boil down to simple calculations involving moving averages and volatility. Access to these indicators is unrestricted for humans (you can view them on most trading platforms), but access to well formatted indicators (csvs instead of visual lines) for large datasets reaching back significantly in time is nearly impossible to find. Even if you pay for a service, API usage limits make putting together such a dataset prohibitively expensive.

The fact that this information is largely kept behind paywalls for large firms with proprietary resources makes me question the fairness of this market. With a data imbalance like this, how can a single trader - a daytrader - expect to make money? I wanted to make this data available to the ML community because it is my hope that bringing this data to the community will help to even the scales. Whether you're just looking to toy around and make a few bucks, or interested in contributing to something larger - a group of people working to develop algorithms to help the "little guy" trade - I hope this dataset will be helpful. To the best of my knowledge, this is the first dataset of its kind, but I hope it is not the last.

Data

• I'd recommend starting here: https://colab.research.google.com/drive/1W6TprjcxOdXsNwswkpm_XX2U_xld9_zZ#offline=true&sandboxMode=true In this notebook, I've uploaded the indicators data and made it available for read access. The notebook will walk you through processing the data and putting it to work building advanced ML models.

• If you'd like to download it directly, you can do so here (31GB): https://drive.google.com/file/d/1HVKWtLWlIZj5yY4T3R1CDSn3c_Nh1lB5/view?usp=sharing

• For legal reasons, I use borismarjanovic's dataset as a baseline, which ends in 2017. If you'd like to update your prices and indicators so your model can trade day to day, I've included instructions and code in the quickstart that should be helpful.

Acknowledgements

• The many online tutorials and specifications which helped me write and test the indicator functions
• borismarjanovic for making public an amazing dataset that I use as a baseline for the colab notebook and the direct download file above
• The many online services that have allowed me to download all the recent price information to augment Boris' dataset (which legally I cannot share, but which helped me develop the infrastructure to update the indicators given new prices data that I share in the quickstart and repo).

Next Steps / Future Directions

• Building inventive models using this dataset to more and more accurately predict stock price movements
• Incorporating arbitrage analysis across stocks
• Hedging
• Options and selling short
• Commodities, currencies, ETFs

Collaboration

If this interests you, reach out! My email is abwilf [at] umich [dot] edu. The repository I used to generate the dataset is here: https://github.com/abwilf/daytrader. I love forks. If you want to work on the project, send me a pull request!

This data is about Pia and Philip business, a married couple. They started their new e-commerce business during the pandemic in 2020 by offering convenience goods online. They began by selling an assortment of masks and disinfectants, but quickly expanded to a wider range of various everyday commodities.

Having both a background in traditional and online retail, they are aware of how distant and impersonal online shopping can feel and, at the same time, how important customer guidance and recommendations are for long-term customer loyalty.

To differentiate themselves from the many other commodity shops, they decided to put an even more significant emphasis on personalized recommendations and offers.

One key element of this strategy is a customized weekly newsletter that personally addresses each of their clients. The newsletter includes user favorites, products similar customers liked, new additions, and special offers. However, they quickly noticed a problem: repeated recommendations of recently purchased products. One quick workaround for this issue was implementing a filter that would exclude products from the recommendation for a fixed number of days. This, however, did not meet the high standards of Pia and Philip.

They are instead looking for a model that can reliably predict the week that a returning customer might repurchase one of their frequently purchased items.

By knowing the estimated week of replenishment, products can be added to the newsletter as a reminder, thus increasing basket sizes and profits.

Since the owners are only interested in the best possible solution, they organized a contest to benchmark competing prediction approaches.

The Data

To create a prediction model, the participants will receive historical transaction and descriptive item data in the form of structured text files (.csv).

The data is provided in four individual files. One file containing the orders ("orders.csv"), one containing descriptive item data ("items.csv"), one containing item and category hierarchy information (category_hierarchy.csv), and a template for the result submission ("submission.csv"). Here are some points to note about the files:

1. The first line (top line) has the same structure as the data sets but contains the names of the respective columns (data fields).
2. A list of all the column names, which occur in the appropriate order, can be found in the "features.pdf" file along with brief descriptions and value ranges for the associated fields.
3. The top row and each data set contain several fields separated from each other by the "|" (pipe) symbol.
4. There is no escape character: quotes are not used.
5. The encoding is "utf-8".

The "items.csv" file is a master data set that contains descriptive features. All features are categorical but numerically encoded. The list of features is explained in the "features.pdf" file. Each data line contains the description for one single item.

The "orders.csv" file contains information about user-specific orders across eight months. Each line displays one transaction for one single item. All attributes are described in the "features.pdf" file.

The "category_hierarchy.csv" file contains two columns of encoded categories, that maps each category to its parent category.

The "submission.csv" file is the reference for submission and contains a predefined subset of userID and itemID combinations as well as an empty "prediction" column for the participants to fill in.

The Task

The goal is to predict the user-based replenishment of a product based on historical orders and item features. Individual items and user specific orders are given for the period between 01.06.2020 and 31.01.2021. The prediction period is between 01.02.2021 and 28.02.2021, which is exactly four weeks long.

For a predefined subset of user and product combinations, the participants shall predict if and when a product will be purchased during the prediction period.

The prediction column in the "submission.csv" file must be filled accordingly.

• 0: no replenishment during that period
• 1: replenishment in the first week
• 2: replenishment in the second week
• 3: replenishment in the third week
• 4: replenishment in the fourth week

Inventory Time Series for Shanghai Ganglian E Commerce. Shanghai Ganglian E-Commerce Holdings Co., Ltd. provides data services for commodities and related industries in the People's Republic of China. The company offers big data and data processing, industrial internet data, software development and sale, enterprise management consulting, conference and exhibition, advertising design, and agency and publication services. It also offers consignment transaction and supply chain services; and steel products and related services. It operates banksteel.com, a steel and silver steel spot online trading platform; and Gangyin e-commerce that provides a package of e-commerce solutions for upstream and downstream users in the steel industry. In addition, the company's services cover various industries, such as ferrous and nonferrous metals, energy, chemical, building materials, agricultural products, extends to new energy, new materials, renewable resources, and other commodity fields. Shanghai Ganglian E-Commerce Holdings Co., Ltd. was founded in 2000 and is headquartered in Shanghai, the People's Republic of China.

Iron Ore rose to 106.94 USD/T on December 1, 2025, up 2.00% from the previous day. Over the past month, Iron Ore's price has risen 1.04%, and is up 1.54% compared to the same time last year, according to trading on a contract for difference (CFD) that tracks the benchmark market for this commodity. Iron Ore - values, historical data, forecasts and news - updated on December of 2025.

Wheat fell to 529.25 USd/Bu on December 1, 2025, down 0.33% from the previous day. Over the past month, Wheat's price has fallen 2.62%, and is down 1.53% compared to the same time last year, according to trading on a contract for difference (CFD) that tracks the benchmark market for this commodity. Wheat - values, historical data, forecasts and news - updated on December of 2025.

The Organic INTEGRITY Database is a certified organic operations database that contains up-to-date and accurate information about operations that may and may not sell as organic, deterring fraud, increases supply chain transparency for buyers and sellers, and promotes market visibility for organic operations. Only certified operations can sell, label, or represent products as organic, unless exempt or excluded from certification. The INTEGRITY database improves access to certified organic operation information by giving industry and public users an easier way to search for data with greater precision than the formerly posted Annual Lists of Certified Operations. You can find a certified organic farm or business, or search for an operation with specific characteristics such as:

The status of an operation: Certified, Surrendered, Revoked, or Suspended The scopes for which an operation is certified: Crops, Livestock, Wild Crops, or Handling

The organic commodities and services that operations offer. A new, more structured classification system (sample provided) will help you find more of what you’re looking for and details about the flexible taxonomy can be found in the INTEGRITY Categories and Items list. Resources in this dataset:Resource Title: Organic INTEGRITY Database. File Name: Web Page, url: https://organic.ams.usda.gov/integrity/Default.aspx Find a specific certified organic farm or business, or search for an operation with specific characteristics. Listings come from USDA-Accredited Certifying Agents. Historical Annual Lists of Certified Organic Operations and monthly snapshots of the full data set are available for download on the Data History page. Only certified operations can sell, label or represent products as organic, unless exempt or excluded from certification.

About This Dataset: Copper Prices and Market Trends

    This dataset provides **insights into copper prices**, including current rates, historical trends, and key factors affecting price fluctuations. Copper is essential in **construction**, **electronics**, and **transportation** industries. Investors, traders, and analysts use accurate copper price data to guide decisions related to **trading**, **futures**, and **commodity investments**.

    ### **Key Features of the Dataset**

    #### **Live Market Data and Updates**
    Stay updated with the latest **copper price per pound** in USD. This data is sourced from exchanges like the **London Metal Exchange (LME)** and **COMEX**. Price fluctuations result from **global supply-demand shifts**, currency changes, and geopolitical factors.

    #### **Interactive Copper Price Charts**
    Explore **dynamic charts** showcasing real-time and historical price movements. These compare copper with **gold**, **silver**, and **aluminium**, offering insights into **market trends** and inter-metal correlations.

    ### **Factors Driving Copper Prices**

    #### **1. Supply and Demand Dynamics**
    Global copper supply is driven by mining activities in regions like **Peru**, **China**, and the **United States**. Disruptions in production or policy changes can cause **supply shocks**. On the demand side, **industrial growth** in countries like **India** and **China** sustains demand for copper.

    #### **2. Economic and Industry Trends**
    Copper prices often reflect **economic trends**. The push for **renewable energy** and **electric vehicles** has boosted long-term demand. Conversely, economic downturns and **inflation** can reduce demand, lowering prices.

    #### **3. Impact of Currency and Trade Policies**
    As a globally traded commodity, copper prices are influenced by **currency fluctuations** and **tariff policies**. A strong **US dollar** typically suppresses copper prices by increasing costs for international buyers. Trade tensions can also disrupt **commodity markets**.

    ### **Applications and Benefits**

    This dataset supports **commodity investors**, **traders**, and **industry professionals**:

    - **Investors** forecast price trends and manage **investment risks**. 
    - **Analysts** perform **market research** using price data to assess **copper futures**. 
    - **Manufacturers** optimize supply chains and **cost forecasts**.

    Explore more about copper investments on **Money Metals**:

    - [**Buy Copper Products**](https://www.moneymetals.com/buy/copper) 
    - [**95% Copper Pennies (Pre-1983)**](https://www.moneymetals.com/pre-1983-95-percent-copper-pennies/4) 
    - [**Copper Buffalo Rounds**](https://www.moneymetals.com/copper-buffalo-round-1-avdp-oz-999-pure-copper/297)

    ### **Copper Price Comparisons with Other Metals**

    Copper prices often correlate with those of **industrial** and **precious metals**:

    - **Gold** and **silver** are sensitive to **inflation** and currency shifts. 
    - **Iron ore** and **aluminium** reflect changes in **global demand** within construction and manufacturing sectors.

    These correlations help traders develop **hedging strategies** and **investment models**.

    ### **Data Variables and Availability**

    Key metrics include:

    - **Copper Price Per Pound:** The current market price in USD. 
    - **Copper Futures Price:** Data from **COMEX** futures contracts. 
    - **Historical Price Trends:** Long-term movements, updated regularly. 

    Data is available in **CSV** and **JSON** formats, enabling integration with analytical tools and platforms.

    ### **Conclusion**

    Copper price data is crucial for **monitoring global commodity markets**. From **mining** to **investment strategies**, copper impacts industries worldwide. Reliable data supports **risk management**, **planning**, and **economic forecasting**.

    For more tools and data, visit the **Money Metals** [Copper Prices Page](https://www.moneymetals.com/copper-prices).

Soybeans rose to 1,130.79 USd/Bu on December 2, 2025, up 0.25% from the previous day. Over the past month, Soybeans's price has risen 0.99%, and is up 14.02% compared to the same time last year, according to trading on a contract for difference (CFD) that tracks the benchmark market for this commodity. Soybeans - values, historical data, forecasts and news - updated on December of 2025.

Palm Oil rose to 4,134 MYR/T on December 2, 2025, up 1.00% from the previous day. Over the past month, Palm Oil's price has risen 0.46%, but it is still 18.56% lower than a year ago, according to trading on a contract for difference (CFD) that tracks the benchmark market for this commodity. Palm Oil - values, historical data, forecasts and news - updated on December of 2025.

Net-Borrowings Time Series for Shanghai Ganglian E Commerce. Shanghai Ganglian E-Commerce Holdings Co., Ltd. provides data services for commodities and related industries in the People's Republic of China. The company offers big data and data processing, industrial internet data, software development and sale, enterprise management consulting, conference and exhibition, advertising design, and agency and publication services; consignment transaction and supply chain services; and steel products and related services. It operates banksteel.com, a steel and silver steel spot online trading platform; and Ganyin e-commerce that provides a package of e-commerce solutions for upstream and downstream users in the steel industry. The company's services cover various industries, such as ferrous and nonferrous metals, energy, chemical, building materials, agricultural products, extends to new energy, new materials, renewable resources, and other commodity fields. The company was founded in 2000 and is headquartered in Shanghai, the People's Republic of China.

Corn rose to 433.53 USd/BU on December 2, 2025, up 0.01% from the previous day. Over the past month, Corn's price has fallen 0.17%, but it is still 2.43% higher than a year ago, according to trading on a contract for difference (CFD) that tracks the benchmark market for this commodity. Corn - values, historical data, forecasts and news - updated on December of 2025.

Copper rose to 5.19 USD/Lbs on December 2, 2025, up 0.35% from the previous day. Over the past month, Copper's price has risen 3.22%, and is up 25.36% compared to the same time last year, according to trading on a contract for difference (CFD) that tracks the benchmark market for this commodity. Copper - values, historical data, forecasts and news - updated on December of 2025.

Orange Juice fell to 147.99 USd/Lbs on December 2, 2025, down 0.38% from the previous day. Over the past month, Orange Juice's price has fallen 15.22%, and is down 71.10% compared to the same time last year, according to trading on a contract for difference (CFD) that tracks the benchmark market for this commodity. Orange Juice - values, historical data, forecasts and news - updated on December of 2025.

Coal fell to 108.35 USD/T on December 1, 2025, down 1.86% from the previous day. Over the past month, Coal's price has fallen 1.14%, and is down 20.33% compared to the same time last year, according to trading on a contract for difference (CFD) that tracks the benchmark market for this commodity. Coal - values, historical data, forecasts and news - updated on December of 2025.