{ "fetched_at": "2026-10-19T17:50:45Z", "source_url": "https://www.kaggle.com/competitions/emory/data", "pages": [ { "name": "data-description", "content": "Coding language: Python\nNote: You don't have to use Python for visualization\n\nDatasets: cryptocurrency (BTC, ETH, USDT, DOGE, SHIBA INU) price and volume information from coinmarketcap.com, the prices of other cryptocurrencies can give you insight on market changes.\nGoal: predict the price of BTC in the next hour where 0=price drops by 0.02% or 1=price goes up by 0.02%\n\nREMEMBER that no one can predict bitcoin change at 100% accuracy. The goal is to make the accuracy as high as possible.\n\nParticipants should be able to answer these types of questions after reading the data description:\n- What am I predicting? \n- What variables are available for prediction?\n- What level of granularity is there in the data?\n\nThe dataset has tracked and produced files for hourly time series pricing data for the crypto market. Each file is in CSV format and can be imported automatically by Python scripts or other automated processes. \n\nIn each file, you will find the following columns. This OHLC (Open/High/Low/Close) pricing data is taken from the daily exchanges.\n\nUnix Timestamp - Also known as \"Epoch Time\". You can convert it to your local time.\nDate - This timestamp is in UTC(Universal Time Coordinated) Time Zone\nSymbol - The symbol for which the time series data refers\nOpen - The opening price of the time period\nHigh - The highest price of the time period\nLow The lowest price of the time period\nClose - The closing price of the time period\nVolume (Crypto) - The volume in the transacted Ccy. Ie. For BTC/USDT, this is in BTC amount\nVolume Base Ccy - The volume in the base/converted ccy. Ie. For BTC/USDT, this is in USDT amount\nTrade Count - The unique number of trades for the given time period", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "IMPORTANT:\nYou must also sign up through the Google form to be considered a participant for this challenge.\nlink: https://forms.gle/kMinDQ8wrGtQP6Ci7\n\nProfessor Rajiv Garg, Goizueta Data Analytics Club, and Information Systems and Operations Management Area proudly present you—Analysts@Emory! Analysts@Emory data analytics challenge is created to get people excited about coding and analytics, and gaining an opportunity to participate in a friendly data analytics challenge at Emory University!\n\nThe goal of the challenge is to utilize the provided datasets to complete the following tasks:\n- Build a prediction model using python (70% of score based on performance matrix)\n- Create visualizations and insights report from the data (20% of score) to explain prediction model (max 4 double spaced pages)\n- Present the finding in a 10-minute in-person presentation during first week of December (10%)\n\nTo sum up, your goal is to build a model that predicts the price change of Bitcoin in the next hour. You will create a binary variable (your target prediction) that is either 0 or 1. Where \"0\" means price drops by 0.01% or more, while 1 means price grows by 0.01% or more.\n\nDatasets: cryptocurrency (BTC, ETH, USDT, DOGE, SHIBU) price and volume information from coinmarketcap.com, which can be accessed through data page. For predictive model, you are allowed to use only the data provided. For the insights report, you can bring in additional data to explain the changes in prices - please cite the data sources and plan to share a link to the data.\n\n\nFor questions please contact any of the owners: \n1. Pandora Shou - ( pandora.shou@emory.edu )\n2. Shivam Bajaj - ( shivam.bajaj@emory.edu )\n3. Shuang Wu - ( shuang.wu@emory.edu )\n4. Yuyao Wang - ( yuyao.wang@emory.edu )", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "Your delivery will be graded based on the following criteria:\n1. model performance based on F-measure (70%)\n2. data visualization & insights (20%)\n3. presentation (10%)\n\n---\n**Model performance based on F-measure**\n\nThe evaluation metric for this competition is [Mean F1-Score](https://en.wikipedia.org/wiki/F-score). The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision and recall\n\nPrecision is the ratio of true positives to all predicted positives. Recall is the ratio of true positives to all actual positives. The F1 score is given by:\n\n![](https://www.gstatic.com/education/formulas2/397133473/en/f1_score.svg)\n\nThe F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.\n\n\n**Data Visualization**\n\nThe grading over data visualization is based on the data ink used (the most information in the least visual elements) and overall aesthetic. \n\n**Presentation**\nThe grading over presentation is based on effective organization of slides and clarity of communication. \n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "You don't have to be a perfectionist. Just try your best and have fun exploring data :)", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Timeline", "content": "November 2, 2021 -- start time\nDec 5, 2021 -- Model & PPT Submission Deadline\nDec 6, 2021 - Dec 10, 2021 -- presentation week, available time spots will be released soon\n\n\nAll deadlines are at 11:59 PM ET on the corresponding day unless otherwise noted. The competition organizers reserve the right to update the contest timeline if they deem it necessary.\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Prizes", "content": "Special thanks for sponsorship from Professor Garg! \nFor the contest this year, we are giving out trophies to every member inside the team. Also, the winners will get a secret surprise gift 👀 \nThe awards will be presented to the following winning teams:\n\n- Highest scoring (winner) undergraduate team\n- Second-highest scoring (runners up) undergraduate team\n- Highest scoring (winner) graduate team\n- Second-highest scoring (runners up) graduate team\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Requirements", "content": "Team Members:\n1. everyone inside your team should be Emory students\n2. your team has 1-3 members. While single players are allowed, we strongly recommend you to build team of 2-3 students. There will be a lot of work, and it will be beneficial for you to divide the task with a friend or just diversify the ideas.\n3. if your team has a graduate student, your team will be automatically categorized as the graduate student team\n\nCoding Language: python", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Submission", "content": "You can make as many submissions as you like, but we will only consider your latest submission before the deadline of December 5th.\n\nIf you are submitting as a team, you do NOT need to merge within the Kaggle platform (it's actually disabled), but all team members must be listed as collaborators on the submitted Notebook, and all team members must accept the competition rules before the submission deadline.\n\nA valid submission will include a Notebook Analysis. All notebooks submitted must be made public on or before the submission deadline to be eligible. If submitting as a team, all team members must be listed as collaborators on all notebooks submitted.\n\nIf you encounter trouble submitting the files on Kaggle, please send the files to Shuang.wu@emory.edu or shivam.bajaj@emory.edu", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }