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！