{
  "fetched_at": "2026-10-19T07:50:19Z",
  "source_url": "https://www.kaggle.com/competitions/convolve-epoch1/data",
  "pages": [
    {
      "name": "data-description",
      "content": "This contest is about **Log Anomaly Detection**\n\nIn computing, logging is the act of keeping a log of events that occur in a computer system, such as problems, errors or just information on current operations. These events may occur in the operating system or in other software. A message or log entry is recorded for each such event. Log Anomaly Detection is simply detecting anomalies in logs deposited by softwares using Machine Learning.\n\nAnomaly is anything that is different from what is usually perceived as normal - an exception. In software engineering, anomaly can be defined as occurrence of rare or unexpected events that does not fit into the normal patterns and hence a suspicious one. Examples could be:\n- Unexpected failure of a service\n- Sudden increase/decrease of user activity in a customer facing system\nReasons for these anomalies could be different, like:\n- Entry of unperceived inputs to the system\n- System running out of memory\n\nYou have been given a training dataset and a testing dataset containing logs generated by softwares. The training dataset is in **JSON** format where each key is a single software log  and coresponding value is the label for that log.The labels for logs are **\"abnormal\" and \"normal\"**. The testing dataset is in **CSV** format with 2 columns corespondinig to a Unique ID and a software log. Your task is to train a ML model on the given training data that can predict whether a given log in testing data is an anomaly or normal. Unique identifier is assigned to each log in testing dataset for ease of evaluation and submission. \n\nPlease note that software logs have a massive number of lines and can be very difficult to handle without crashing memory and RAM.\n\n\n## Files\n\n*   **train.json** - the training dataset\n*   **test.csv** - the test dataset\n*   **sample_submission.csv** - a sample submission file in the correct format",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "#Welcome Dear Participant!\nFor the first time ever, **6 IITs along with Cisco** have come together to organize Convolve, an ML/AI Hackathon like no other! So if you are a Data Science enthusiast and often wonder how you fare against the sharpest minds, then this is the chance to test your mettle! You MUST register your team on Unstop to offically be a participant in this competition: https://unstop.com/hackathon/convolve-a-mlai-hackathon-for-the-future-cisco-524330\nPlease read the rules section of this contest.\n\n#About Convolve\nThe competition aims to spotlight some of the finest practitioners of Data Science and pit them against each other. The competition has **prizes worth more than 2 Lacs**! The participants are expected to be well versed with the methods of Machine Learning, Data Analytics and how real-life Industry problems are solved using them.It is open for all and consists of **3 rounds**. The first two rounds will be online and the final round will be hosted offline at the campus of IIT-Guwahati. This is the contest for the first round.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation pages describes how submissions will be scored and how students should format their submissions. You don't need a sub-title at the top; the page title appears above. For an example of a high quality evaluation page, see the 2013 KDD Cup page, which we have included below:\n\n---\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$$\\text{F1} = 2\\frac{\\text{precision} \\cdot \\text{recall}}{\\text{precision}+\\text{recall}}\\ \\ \\mathrm{where}\\ \\ \\text{precision} = \\frac{\\text{true positives}}{\\text{true positives}+\\text{false positives}},\\ \\ \\text{recall} = \\frac{\\text{true positives}}{\\text{true positives}+\\text{false negatives}}$$\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## Submission Format\n\nA valid submission file should contain two columns: \"ID\" and \" Label\". The \"ID\" column for the submission should match with \"ID\" column in the testing dataset provided. For each row, \" Label\" should correspond to your detection of the \"Log\" that corresponds to that \"ID\" in the provided test dataset. Take a look at sample_submissions.csv to understand better. Contact organizers through Unstop in case of any queries. \n\nIMPORTANT NOTE: In your csv file, the top row should be: [\"ID\", \" Label\"] and not [\"ID\", \"Label\"]. Notice the space before Label.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "You must accept these rules before participating in this contest:\n\n - Team Size: Minimum 2 and Maximum 4\n - Each Participant MUST only be a part of ONE team\n - Your Team name on the Leaderboard MUST be same as registered on [Unstop Page](https://unstop.com/hackathon/convolve-a-mlai-hackathon-for-the-future-cisco-524330), otherwise your final submission will not be considered.\n - Only top 100 teams on private leaderboard will move on to the next epoch\n - Violation of any rule may lead to disqualification of entire team\n - The organizing team reserves the right to change the rules at any point in time",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}