** Notice: all internal pipelines have been restricted to 30 minute timeouts, if your CI/CD runs take longer, either use your own runners or read below **
We would remind everyone that the CI/CD services provided by the university Gitlab servers are intended for CI/CD use only (ie. delivering new versions of your software to your production servers, etc).They are not intended for data analysis or -production use, or creating, building and running servers to do heavy data calculation or visualization.
As a general guideline; if your jobs take more than 15 minutes, you might be running something that is better suited for a dedicated system or a virtual server - in this case, please contact the helpdesk for a solution to your needs.
I’d say we accomplished the best we could with this dataset. After trying many models with many parameters, and after trying boosting methods and stacking methods, I’d say, the we’ve reached very close to the best possible score with this dataset. Many things affect the price of the house, that we just don’t have knowledge of in this dataset, for example “vastike”, the full “huoneisto” text, more spesific location, renovations and more. The model we achieved can give a great ballpark guess of the price area, but not determine the final price without a human seller and human buyer. This could be used as online tool for people thinking of selling or buying an house, and giving them intuition on house price. And maybe give info about the model in advance, that this is more accurate on bigger cities and with flats.
I’d say we accomplished the best we could with this dataset. After trying many models with many parameters, and after trying boosting methods and stacking methods, I’d say, the we’ve reached very close to the best possible score with this dataset. Many things affect the price of the house, that we just don’t have knowledge of in this dataset, for example “vastike”, the full “huoneisto” text, more spesific location, renovations and more. The model we achieved can give a great ballpark guess of the price area, but not determine the final price without a human seller and human buyer. This could be used as online tool for people thinking of selling or buying an house, and giving them intuition on house price. And maybe give info about the model in advance, that this is more accurate on bigger cities and with flats.
