Since the training data ranged from 2017-03-1 to 2018-03-31, we couldn't do much with the year. In order to add some temporal context, we included stock market indices such as the S&P 500 and the DOW JONES.
", "messages": [ { "id": "1912722", "postDate": "08/25/2022 00:20:03", "content": "Since the training data ranged from 2017-03-1 to 2018-03-31, we couldn't do much with the year. In order to add some temporal context, we included stock market indices such as the S&P 500 and the DOW JONES.
", "rawMarkdown": "Since the training data ranged from 2017-03-1 to 2018-03-31, we couldn't do much with the year. In order to add some temporal context, we included stock market indices such as the S&P 500 and the DOW JONES.", "votes": null }, { "id": "1912727", "postDate": "08/25/2022 00:22:04", "content": "Great idea! And congrats!
", "rawMarkdown": "Great idea! And congrats!", "votes": null }, { "id": "1912730", "postDate": "08/25/2022 00:22:41", "content": "Were we allowed to use external data?
", "rawMarkdown": "Were we allowed to use external data?", "votes": null }, { "id": "1912751", "postDate": "08/25/2022 00:34:54", "content": "As mentioned in Rule B.7.C, yes if it is public available
", "rawMarkdown": "As mentioned in Rule B.7.C, yes if it is public available", "votes": null }, { "id": "1912784", "postDate": "08/25/2022 01:04:27", "content": "Congrats! I was expecting some nice macro economics ideas. I only thought about that too late on the competition, was anxious to see if it worked. Could you tell what score a single model like this can achieve?
", "rawMarkdown": "Congrats! I was expecting some nice macro economics ideas. I only thought about that too late on the competition, was anxious to see if it worked. Could you tell what score a single model like this can achieve?", "votes": null }, { "id": "1912822", "postDate": "08/25/2022 01:35:04", "content": "May I ask why you guys used ETF fund indexes in the first place? Is it based on the assumption that there may be correlation between financial market health and an individuals ability to pay back his credit card payments? Thanks~
", "rawMarkdown": "May I ask why you guys used ETF fund indexes in the first place? Is it based on the assumption that there may be correlation between financial market health and an individuals ability to pay back his credit card payments? Thanks~", "votes": null }, { "id": "1912869", "postDate": "08/25/2022 02:36:30", "content": "Good idea. Congratulations!
", "rawMarkdown": "Good idea. Congratulations!", "votes": null }, { "id": "1913068", "postDate": "08/25/2022 05:47:00", "content": "Amazing intuition!
", "rawMarkdown": "Amazing intuition!", "votes": null }, { "id": "1913832", "postDate": "08/25/2022 14:29:23", "content": "Great approach! I am glad that this led to a great result and a deserving medal winning position as well! Congratulations @danielgallo !!!
", "rawMarkdown": "Great approach! I am glad that this led to a great result and a deserving medal winning position as well! Congratulations @danielgallo !!!", "votes": null }, { "id": "1914242", "postDate": "08/25/2022 21:52:09", "content": "As @chenjunlin99 said, we were allowed since it was publicly available information. In particular, we obtained the Dow Jones data from here and the S&P 500 data from here.
", "rawMarkdown": "As @chenjunlin99 said, we were allowed since it was publicly available information. In particular, we obtained the Dow Jones data from [here](https://www.wsj.com/market-data/quotes/index/DJIA/historical-prices) and the S&P 500 data from [here](https://www.wsj.com/market-data/quotes/index/SPX/historical-prices).", "votes": null }, { "id": "1914245", "postDate": "08/25/2022 21:59:09", "content": "In the beginning we did some testing with a simple XGB model, and the version that included the stock market indices yielded a CV that was 0.002 higher. I just ran the models again and CVs were 0.777 and 0.779 (as I said, the model trained on a really simple dataset😬). After that, we included the stock market indices in every dataset we created.
", "rawMarkdown": "In the beginning we did some testing with a simple XGB model, and the version that included the stock market indices yielded a CV that was 0.002 higher. I just ran the models again and CVs were 0.777 and 0.779 (as I said, the model trained on a really simple dataset😬). After that, we included the stock market indices in every dataset we created.", "votes": null }, { "id": "1914248", "postDate": "08/25/2022 22:04:47", "content": "We thought that if the economic situation worsens, some individuals might find it hard to meet their payments.
", "rawMarkdown": "We thought that if the economic situation worsens, some individuals might find it hard to meet their payments.", "votes": null }, { "id": "1914262", "postDate": "08/25/2022 22:59:10", "content": "How was it included? The correlation makes sense, but not sure how to use it in practice.
", "rawMarkdown": "How was it included? The correlation makes sense, but not sure how to use it in practice.", "votes": null } ], "comments": [ { "id": 1912727, "author_name": "julianmukaj", "author_url": "", "post_date": "08/25/2022 00:22:04", "content": "Great idea! And congrats!
", "votes": null, "replies": [] }, { "id": 1912730, "author_name": "alexandreg1998", "author_url": "", "post_date": "08/25/2022 00:22:41", "content": "Were we allowed to use external data?
", "votes": null, "replies": [ { "id": 1912751, "author_name": "chenjunlin99", "author_url": "", "post_date": "08/25/2022 00:34:54", "content": "As mentioned in Rule B.7.C, yes if it is public available
", "votes": null, "replies": [] }, { "id": 1914242, "author_name": "danielgallo", "author_url": "", "post_date": "08/25/2022 21:52:09", "content": "As @chenjunlin99 said, we were allowed since it was publicly available information. In particular, we obtained the Dow Jones data from here and the S&P 500 data from here.
", "votes": null, "replies": [] } ] }, { "id": 1912784, "author_name": "hinepo", "author_url": "", "post_date": "08/25/2022 01:04:27", "content": "Congrats! I was expecting some nice macro economics ideas. I only thought about that too late on the competition, was anxious to see if it worked. Could you tell what score a single model like this can achieve?
", "votes": null, "replies": [ { "id": 1914245, "author_name": "danielgallo", "author_url": "", "post_date": "08/25/2022 21:59:09", "content": "In the beginning we did some testing with a simple XGB model, and the version that included the stock market indices yielded a CV that was 0.002 higher. I just ran the models again and CVs were 0.777 and 0.779 (as I said, the model trained on a really simple dataset😬). After that, we included the stock market indices in every dataset we created.
", "votes": null, "replies": [] } ] }, { "id": 1912822, "author_name": "hwan18", "author_url": "", "post_date": "08/25/2022 01:35:04", "content": "May I ask why you guys used ETF fund indexes in the first place? Is it based on the assumption that there may be correlation between financial market health and an individuals ability to pay back his credit card payments? Thanks~
", "votes": null, "replies": [ { "id": 1914248, "author_name": "danielgallo", "author_url": "", "post_date": "08/25/2022 22:04:47", "content": "We thought that if the economic situation worsens, some individuals might find it hard to meet their payments.
", "votes": null, "replies": [] } ] }, { "id": 1912869, "author_name": "cdeotte", "author_url": "", "post_date": "08/25/2022 02:36:30", "content": "Good idea. Congratulations!
", "votes": null, "replies": [] }, { "id": 1913068, "author_name": "kaggledummie007", "author_url": "", "post_date": "08/25/2022 05:47:00", "content": "Amazing intuition!
", "votes": null, "replies": [] }, { "id": 1913832, "author_name": "ravi20076", "author_url": "", "post_date": "08/25/2022 14:29:23", "content": "Great approach! I am glad that this led to a great result and a deserving medal winning position as well! Congratulations @danielgallo !!!
", "votes": null, "replies": [] }, { "id": 1914262, "author_name": "roberthatch", "author_url": "", "post_date": "08/25/2022 22:59:10", "content": "How was it included? The correlation makes sense, but not sure how to use it in practice.
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "1912722": "Since the training data ranged from 2017-03-1 to 2018-03-31, we couldn't do much with the year. In order to add some temporal context, we included stock market indices such as the S&P 500 and the DOW JONES.", "1912727": "Great idea! And congrats!", "1912730": "Were we allowed to use external data?", "1912751": "As mentioned in Rule B.7.C, yes if it is public available", "1912784": "Congrats! I was expecting some nice macro economics ideas. I only thought about that too late on the competition, was anxious to see if it worked. Could you tell what score a single model like this can achieve?", "1912822": "May I ask why you guys used ETF fund indexes in the first place? Is it based on the assumption that there may be correlation between financial market health and an individuals ability to pay back his credit card payments? Thanks~", "1912869": "Good idea. Congratulations!", "1913068": "Amazing intuition!", "1913832": "Great approach! I am glad that this led to a great result and a deserving medal winning position as well! Congratulations @danielgallo !!!", "1914242": "As @chenjunlin99 said, we were allowed since it was publicly available information. In particular, we obtained the Dow Jones data from [here](https://www.wsj.com/market-data/quotes/index/DJIA/historical-prices) and the S&P 500 data from [here](https://www.wsj.com/market-data/quotes/index/SPX/historical-prices).", "1914245": "In the beginning we did some testing with a simple XGB model, and the version that included the stock market indices yielded a CV that was 0.002 higher. I just ran the models again and CVs were 0.777 and 0.779 (as I said, the model trained on a really simple dataset😬). After that, we included the stock market indices in every dataset we created.", "1914248": "We thought that if the economic situation worsens, some individuals might find it hard to meet their payments.", "1914262": "How was it included? The correlation makes sense, but not sure how to use it in practice." }, "source": "meta" }