建立有利可图的预测模型 [英] Building profitable prediction model
问题描述
大家好!
我正在寻找一种方法来开发成功投注的模型。
I am looking for a way to develop a model for successful betting.
我有一个数据库100k系列的体育赛事,通过使用excel及其过滤器,我开发出的策略看起来非常好+156分,最大提取率约为20%。
I have the database with 100k lines of sports events and by using excel and its filters i've developed the strategy that looks very good +156 points and maximum withdraw about 20%.
我已经开始使用Azure ML工作室进行实验,但是我找不到可以构建评估不完全匹配的模型的方法,而是使用excel过滤器完成整个策略。
I've started my experiments with Azure ML studio but i couldn't find the way i can build the model that evaluates not exact match, but whole strategy as i did it with excel filters.
我这里有几个匹配功能:
I have here several features of match:
f1:1.58
f2: 0.94
f2: 0.94
f3:509.5
和奖励对于失败的玩家获胜(1.59),在Excel中我通过总结所有失败者获胜和损失列的利润来评估盈利能力,结果我的投资回报率约为23%。
and reward for underdog player winning (1.59), in Excel i evaluate profitability by summarizing profit of all underdog wins and losses column and in result i have ROI of around 23%.
那么是否有技术可以在我的情况下使用吗?
So is there a technology that can be used in my case?
推荐答案
Hi,
您可以浏览一些示例,看看是否可以重复使用用例中使用的一些技术: https://gallery.azure.ai/
You could browse through some examples to see if you can reuse some of the techniques used in your use case: https://gallery.azure.ai/
这是一个可能有用的备忘单: https://docs.microsoft.com/en-us/azure/machine-learning/studio/ algorithm-cheat-sheet
Here is a cheat sheet that might be helpful: https://docs.microsoft.com/en-us/azure/machine-learning/studio/algorithm-cheat-sheet
以下是一些产品文档: https://docs.microsoft.com/en-us/azure / machine-learning /
Here is some product documentation: https://docs.microsoft.com/en-us/azure/machine-learning/
问候,
Jaya
Regards,
Jaya
>
这篇关于建立有利可图的预测模型的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!