Decision tree looks inaccurate
notacoolpotato Member Posts: 1 Contributor I
Hey guys, I am fairly new to using rapid miner and in this dataset, I'm trying to analyze the viability of a property (based on the reviews, overall satisfaction and the date listed). So I have used filter example to eliminate data records that do not have a review nor a satisfaction rate, because I'm assuming the properties must have been listed very recently. To set constraints where I can access the 'viability' (generated attribute) better, I wrote an expression where reviews (attribute) and overall satisfaction (attribute) must be above their average number respectively. Then I set 'viability' as my label and split data into 0.7 and 0.3. But when I run the whole process, my decision tree only takes into account the reviews. Besides, I'd imagine my decision tree to be more thorough and larger with more branches. I'm not sure where I'm going wrong. Any help would be appreciated. I've attached some screenshots for your reference too!