{
  "fetched_at": "2026-10-20T07:27:21Z",
  "source_url": "https://www.kaggle.com/competitions/2023-psl-week-using-bloomberg-news/data",
  "pages": [
    {
      "name": "data-description",
      "content": "**Sentiment Scores:** A time-series dataset of sentiment scores, calculated from news articles, social media posts, and financial reports. These scores range from highly negative to highly positive, encapsulating public sentiment towards different stocks or the market as a whole.\n\n**Market Data:** forward returns of a hidden market.\n\n**Task:**\nParticipants are required to develop a regression model that predicts the future returns of stocks based on their sentiment scores. The goal is to accurately forecast the percentage change in a stock's price over a predefined future time horizon.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Submissions will be evaluated based on the Root Mean Squared Error (RMSE) between the predicted and actual stock returns. The lower the RMSE, the higher the accuracy of the prediction, and thus the better the model.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions will be evaluated based on the Root Mean Squared Error (RMSE) between the predicted and actual stock returns. The lower the RMSE, the higher the accuracy of the prediction, and thus the better the model.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "PSL Week Kaggle rules are quite intuitive:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Title: PSL Week Kaggle Challenge: Predicting Future Returns from Sentiment Scores\n\n**Background:**\nIn the ever-evolving world of financial markets, the interplay between public sentiment and market performance has long been a topic of interest for both researchers and practitioners. The PSL (Predictive Stock League) Week Kaggle Competition aims to delve into this relationship by leveraging the power of data science and machine learning.\n\n**Challenge Overview:**\nThis unique competition invites Kaggle's vibrant community of data scientists to develop innovative models that predict future stock returns based on sentiment scores. Participants are provided with a comprehensive dataset that includes sentiment scores derived from various sources, alongside relevant financial market data.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}