创作者变现与加热
最近一段时间都在做一些跟创作者相关的业务,相较于商业传统的三方(平台、用户、广告主),创作者是随着内容平台崛起而诞生的第四方,与其他三方的关系可以参考笔者之前文章 Yet Another Overview of an AD System
本文也是对之前的文章里创作者相关的部分做进一步的展开,主要是商机和加热两大块,前者主要是包括对商机部分中涉及到的各个链路的职责,以及各个链路之间的联动关系;加热中的自投与代投的产品形态,以及在流量上与广告流量的协同关系等。
最近一段时间都在做一些跟创作者相关的业务,相较于商业传统的三方(平台、用户、广告主),创作者是随着内容平台崛起而诞生的第四方,与其他三方的关系可以参考笔者之前文章 Yet Another Overview of an AD System
本文也是对之前的文章里创作者相关的部分做进一步的展开,主要是商机和加热两大块,前者主要是包括对商机部分中涉及到的各个链路的职责,以及各个链路之间的联动关系;加热中的自投与代投的产品形态,以及在流量上与广告流量的协同关系等。
之前写的 An Overview of an AD System, 从技术原理上介绍了各个模块(召回、精排、出价、冷启动等)的基本职责和原理,几年过去了,这部分的认知虽然还没过时,但是经历了更多业务后,对整体的商业化也有一个更全面认知,本文尝试从另一个更系统的角度去理解一个广告系统
传统认知中的 ad system 一般是三方:广告主 / 代理、平台、用户;但是随着内容平台(如抖音、快手、小红书、bilibili 等)的迅速发展,涌现了越来越多的 UGC 内容,创作者在商业变现中的影响也越来越难被忽视,所以这里基于三方增加了代表创作者的第四方,如下图所示
以上的四方比较复杂的关系,一般是存在于 “一方流量”(参考一方数据的概念)上,即抖音 / 快手 / 小红书 /bilibili 这类有能力搭建自己的一方流量的变现团队,在自家的流量上变现;相较于 “一方流量”,“三方流量” 的场景一般只需要关注客户和平台的关系,典型的就是联盟的场景(穿山甲、优量汇、快手联盟等),对用户侧没有强体验约束,因为本质上联盟就是个倒卖流量的生意,相关技术与一方流量差不多,但是对 C 端的用户体验以及创作者部分基本不怎么关注。
本文重点在一方流量上,下面的内容会根据上图中提到四方依次讨论每一方本身的一些职责、与其他各方的关系,内容会比较发散,祝开卷有益~
《Systematic Trading: A unique new method for designing trading and investing systems》 is a comprehensive guide for traders and investors seeking a structured approach to the markets.
Aimed at both novices and experienced traders, the book offers practical insights and applications, making it a pretty good resource for anyone looking to enhance their trading methodology with a systematic approach.
This is not a book totally about automating trading strategies. It’s possible to trade systematically using an entirely manual process with just a spreadsheet to speed up calculations, so automation is not necessary, the key word if "systematic". This passage mainly covers the first two chapters, providing a rough overview of this book. Hope you can enjoy it
最近半年经历了一些业务与组织上的变化,对于这部分也有了一些新的理解和体会,值得写一篇文章来梳理与总结。本文主要讲了对业务和组织的一些看法,包括如何看待 “矛盾” 的业务定位和观点、组织的进化过程、团队组建里的识人与用人等;以及在这个过程中,该如何调整自己的心态。文章比较发散,纯属个人碎碎念,祝开卷有益
"Quantitative Trading: How to Build Your Own Algorithmic Trading Business" by Ernie Chan is a comprehensive guide that explores the world of quantitative trading and provides practical advice for building a algorithmic trading business, especially for individuals interested in quantitative trading.
It covers essential concepts, methodologies, and practical tips to help readers develop and implement their own algorithmic trading strategies while effectively managing risk and building a sustainable trading business.
Due to the significant benefits I received from reading this book, I want to write down some of the most important takeways I get from this book, with the hope that it can also be useful to you.
This passage is about the last four chapters, which introduces execution system in actual trading(automated and semi-automated), how to minimize transaction cost and determine the optimal leverage using the Kelly Criterion. It also talks about some special topics or common sense in trading. Finally, it lists some advantages of individuals investors over institutional investors.
"Quantitative Trading: How to Build Your Own Algorithmic Trading Business" by Ernie Chan is a comprehensive guide that explores the world of quantitative trading and provides practical advice for building a algorithmic trading business, especially for individuals interested in quantitative trading.
It covers essential concepts, methodologies, and practical tips to help readers develop and implement their own algorithmic trading strategies while effectively managing risk and building a sustainable trading business.
Due to the significant benefits I received from reading this book, I want to write down some of the most important takeways I get from this book, with the hope that it can also be useful to you.
This passage is about the first four chapters, which introduce basic requirements for independent traders, including search for ideas, perform backtest, and what we need before conducting real trading.
"The Almanack of Naval Ravikant" is a book that compiles the wisdom and insights of entrepreneur and investor Naval Ravikant. This book mainly talks about two topics, wealth and happiness. It offers practical advice on how to live a more fulfilling and purposeful life.
Through his own experiences and perspectives, Naval provides readers with valuable insights into topics like success, motivation, and personal growth, making the book a useful guide for anyone looking to improve their life and achieve their goals
I have benefited greatly from reading this book, and I want to write some important takeaways from this book. As this book was written in English, I want to give it a try to write it in English, too. Hoping it will be beneficial to you, this passage is about the second topic: Happiness
The passage about the first topic: wealth, can be found here
"The Almanack of Naval Ravikant" is a book that compiles the wisdom and insights of entrepreneur and investor Naval Ravikant. This book mainly talks about two topics, wealth and happiness. It offers practical advice on how to live a more fulfilling and purposeful life.
Through his own experiences and perspectives, Naval provides readers with valuable insights into topics like success, motivation, and personal growth, making the book a useful guide for anyone looking to improve their life and achieve their goals
I have benefited greatly from reading this book, and I want to write some important takeaways from this book. As this book was written in English, I want to give it a try to write it in English, too. Hoping it will be beneficial to you, this passage is about the first topic: Wealth
在搜广推相关业务中,除了 ctr、cvr 这类常规的二分类任务,还存在着预估 stay_duration、LTV、ECPM、GMV 等一系列回归任务
ctr、cvr 这类二分类任务常用的损失函数是交叉熵损失,基本假设是事件服从伯努利分布,最终学习的输出是正样本的比例,而回归任务中存在着非常多种的损失函数可选,如 mse、mae、huber loss、log-normal、weighted logistics regression、softmax 等
每种损失函数都有其假设和适用范围,如果真实 label 分布与假设差异较大,容易导致结果不佳,因此,本文会重点关注这些常见 loss 的推导过程以及假设
在实际的业务中,数据往往由多个 domain 组成,以广告为例,往往会存在多个转化目标,在 ctr、cvr 的预估时也要考虑不同转化目标的影响,因为在不同转化目标下,ctr、cvr 的分布 (如均值、方差) 往往是不一致的
解决这个问题最直观的思路是加 domain 相关特征或根据 domain 拆模型,前者属于隐式的方法,需要特征的区分性足够强、能被模型学到,但这个足够强没有一个量化的标准,基本只能看实验效果;后者则存在维护成本过高的问题,比如说有 n 个 domain 就要拆成 n 个模型
本文着重讲如何通过一个模型 serve 多个 domain 的方法,主要是在业界验证有收益且公开发表的工作,基本上可以分为 3 类