It uses machine learning to go through every single possible iteration of a solution. There is the excel function of whatif. But this goes a step further by taking into all your considerations and maximize profit. Though it would be much stronger if you put in mats and cost.
-
-
Replying to @ZachYesterday @ryanaeckles
It's also easy to use. Just hard to pick up the first time. But it's worth it weight in gold once you set it up.
1 reply 0 retweets 1 like -
Replying to @ZachYesterday @ryanaeckles
Lol I have more thoughts now that this notification came up. Let's say I only want to craft 200k of things but still maximize selling my entire stock. Have a place for smartavgbuy and it can go through and calculate what items to craft. How many and what items will sell within
1 reply 0 retweets 0 likes -
Replying to @ZachYesterday @ryanaeckles
Ah gosh I have too many words! Nerual networks are so goooood!
1 reply 0 retweets 0 likes -
Replying to @ZachYesterday
That's really cool. I'll get in and play around with it. You could also geek out with
@thegoldqueen about this cause she went and got degreed in it1 reply 0 retweets 1 like -
-
It's so so tempting to just throw the whole lot at machine learning and proceed straight to "win".
1 reply 0 retweets 2 likes -
Replying to @thegoldqueen @ryanaeckles
Well clearly it may not be that easy. But I think using a basic LSTM network might be useful for short term forecasting. It won't be a "win" but it will help gold makers make smarter decisions.
2 replies 0 retweets 1 like -
Replying to @ZachYesterday @ryanaeckles
On a per-product basis or per profession maybe
1 reply 0 retweets 0 likes -
Replying to @thegoldqueen @ryanaeckles
Yeah so my idea is connecting craftables with supply chains and measure the price of materials with quantity to see when it's good to invest with a higher level of certainty.
1 reply 0 retweets 0 likes
I think we would learn something about farm bot activity!
-
-
Replying to @thegoldqueen @ryanaeckles
Oh right like a 500% change between the projected and the actual. Might want to look into that.
1 reply 0 retweets 0 likes -
Replying to @ZachYesterday @ryanaeckles
I think the model would discover and then expect a peak in mats dumps at 5am and then get worried and alarmed if bots stopped
1 reply 0 retweets 0 likes - Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.