By Gerd Wittchen

蓋德·維琴

推薦解決方案的動機 (Motivation for recommendation solutions)

Rapid changes in customer behaviour requires businesses to adapt at an ever increasing pace. The recent changes to our work and personal life has forced entire nations to work remotely and do all non essential shopping online. With every challenge in business there is opportunity on the other side.

客戶行為的快速變化要求企業以不斷提高的速度適應。 我們工作和個人生活的最新變化迫使整個國家進行遠程工作，并進行所有非必需的在線購物。 面對業務中的每一項挑戰，另一邊都有機會。

According to a techcrunch.com report, US e-commerce sales went up by 49% in April, in comparison with the baseline period in early March. This subsequently led to a flood of digital campaigns and initiatives fighting for attention.

根據techcrunch.com的報告，與3月初的基準時期相比，4月份美國的電子商務銷售額增長了49％。 隨后導致大量的數字運動和倡議在爭取關注。

We think that businesses who want to stay relevant in such a competitive environment must understand how to best add value to their customers and more importantly, respect their time.

我們認為，想要在競爭激烈的環境中保持聯系的企業必須了解如何最大程度地為其客戶增加價值，更重要的是，尊重他們的時間。

In a rapidly changing environment it is critical for an organisation to develop situational awareness, which feeds into a business adjustment process. The adjustment process in this context, is the time an organisation or business requires to react to change in their underlying market condition.

在瞬息萬變的環境中，對于組織而言，發展態勢感知至關重要，這會影響到業務調整流程。 在這種情況下，調整過程是組織或企業需要對其基本市場狀況的變化做出React的時間。

One example of an adjustment process framework is the OODA Loop (Observe, Orient, Decide, Act) which was developed by John Boyd — a military strategist whose theories are now widely applied in law enforcement and business.

調整過程框架的一個例子是OODA循環 (觀察，東方，決定，行為)，該理論是由軍事戰略家約翰·博伊德(John Boyd)開發的，其理論現已廣泛應用于執法和商業領域。

Boyd suggests that each and every one of our decision-making processes run in a recurring cycle of Observe — Orient — Decide — Act. An individual or business who is capable of operating in this cycle quickly — observing, orientating and deciding rapidly to reach an action decision with ease — is able to ‘get inside’ another’s cycle to gain a strategic advantage.

博伊德建議，我們的每個決策過程都應遵循“觀察-東方-決定-行動”的周期性循環。 能夠快速地在此周期中進行操作的個人或企業-觀察，定向和快速做出輕松地做出行動決定的決定-能夠“融入”另一個人的周期中以獲得戰略優勢。

面向企業的OODA Loop (OODA Loop for businesses)

觀察 (Observe)

The entire process begins with the observation of data from the world, environment and situation. Situational awareness for a business means to establish a baseline for their customers through methods such as market analysis and research.

整個過程始于觀察來自世界，環境和情況的數據。 企業的態勢感知意味著通過市場分析和研究等方法為客戶建立基準。

東方 (Orient)

This is the moment that we take in all the information garnered during the observation phase and begin to process it. Typically in the form of dashboards and reports to support the business analysis. Within larger organisations, this information tends to be distributed across different systems. Here we typically see the biggest divergence on how quick a business can produce those reports and metrics to keep up with trend changes.

這是我們吸收在觀察階段獲得的所有信息并開始處理它的時刻。 通常以儀表板和報告的形式來支持業務分析。 在較大的組織中，此信息往往分布在不同的系統中。 在這里，我們通常會看到最大的差異，即企業能夠多快地生成這些報告和指標以跟上趨勢變化的步伐。

決定 (Decide)

Decide will be the outcome of — and is entirely reliant on — your orienting phase. If your orientation is lacking information or is using inaccurate information, a potential decision might be ineffective or worse working against its purpose. The idea here is to derive an hypothesis on how to best react to the situation. Knowing the likely outcomes of certain practices and decisions can have overlap onto others. It is important that the outcomes of your previous experience and your orienting phase gets you as close to an accurate prediction of your future actions and impacts as possible.

決定將是您的定向階段的結果，并且完全取決于該階段。 如果您的方向缺少信息或使用的信息不正確，則潛在的決策可能無效或不利于達成目標。 這里的想法是得出關于如何對情況做出最佳React的假設。 知道某些做法和決定的可能結果可能與其他做法重疊。 重要的是，您先前的經驗和導向階段的結果將使您盡可能地準確地預測未來的行為和影響。

法案 (Act)

Act is the final part of the OODA Loop. However, as it is a cycle, any information which you gather from the results of your actions can be used to restart the analytical process. This would include making changes to your business strategy and starting the observation phase again.

Act是OODA Loop的最后一部分。 但是，由于這是一個循環，您從操作結果中收集的任何信息都可以用于重新啟動分析過程。 這將包括更改您的業務策略并再次開始觀察階段。

加快循環 (Speeding up the loop)

For businesses, an efficient loop can allow them to gain a competitive advantage over others in the market. If you’re thinking faster than them, you will be better than them.

對于企業而言，有效的循環可以使他們獲得與市場上其他企業相比的競爭優勢。 如果您比他們想的要快，那您將比他們更好。

If organisations are automating the collection and analysis of observations, it allows them to build powerful capability to surface relevant products/content to customers. This makes recommender systems a key component of all successful online business. From e-commerce, streaming and news to online advertising, recommender systems are today’s automated OODA loops.

如果組織要自動收集和分析觀察結果，則可以使組織建立強大的功能來向客戶展示相關產品/內容。 這使得推薦系統成為所有成功在線業務的關鍵組成部分。 從電子商務，流媒體和新聞到在線廣告，推薦系統是當今的自動化OODA循環。

推薦系統 (Recommender systems)

On a general level, recommender systems are algorithms that predict relevant items to users.

一般而言，推薦系統是一種可以預測與用戶相關項目的算法。

Recommender systems are critical for certain online industries and are worth high rewards to large corporations such a netflix.

推薦系統對于某些在線行業至關重要，對于諸如netflix這樣的大公司來說，值得推薦。

On a high level, there are two classes of recommender systems — collaborative filtering methods and content based methods.

在較高級別上，有兩類推薦系統：協作過濾方法和基于內容的方法。

協同過濾方法 (Collaborative filtering methods)

Collaborative filtering methods for recommender systems are based solely on the past interactions recorded between the users and items in order to produce new recommendations. Those interactions are typically stored in a user-item interactions matrix.

推薦系統的協作過濾方法僅基于用戶和項目之間記錄的過去交互，才能產生新的推薦。 這些交互通常存儲在用戶項交互矩陣中。

The main idea is that past user-item interactions are sufficient to detect similar users and/or similar items and make predictions based on these estimated relationships.

主要思想是，過去的用戶-項目交互足以檢測相似的用戶和/或相似的項目，并基于這些估計的關系進行預測。

Collaborative filtering can be distinguished into two main categories — memory based approach and model based approach.

協作過濾可以分為兩大類：基于內存的方法和基于模型的方法。

基于內存的方法 (Memory based approach)

Memory basedcollaborative filtering again splits into two subcategories — user-to-user or item-to-item — based recommendations.

基于內存的協作篩選再次分為基于用戶對用戶或項目對項目的兩個子類別。

User-to-user collaborative filtering: Users who are similar to you also liked…

用戶到用戶的協作過濾：與您相似的用戶也喜歡…

Item-to-item collaborative filtering: Users who liked this item also liked…

逐項協作過濾：喜歡此項目的用戶也喜歡…

The main idea is that we are not learning any parameter using gradient descent (or any other optimisation algorithm). Similar users or items are calculated only by using distance metrics such as Cosine Similarity or Pearson Correlation Coefficients, which are based on arithmetic operations.

主要思想是我們不會使用梯度下降(或任何其他優化算法)來學習任何參數。 僅通過使用基于算術運算的距離度量(例如余弦相似度或Pearson相關系數)來計算相似的用戶或項目。

基于模型的方法 (Model based approach)

Model based collaborative filtering is developed using machine learning algorithms to build a representation of the information. Predications are then generated using the trained models, rather than distance metrics used in the memory based approach.

使用機器學習算法開發基于模型的協作過濾，以構建信息的表示形式。 然后使用經過訓練的模型而不是基于內存的方法中使用的距離度量來生成預測。

The main advantage of collaborative filtering approaches is that they require no information about users or items, so they can be used in many situations. These algorithms improve with the number of interactions recorded over time (increased dataset).

協作過濾方法的主要優點是它們不需要有關用戶或項目的信息，因此可以在許多情況下使用。 隨著時間的推移，這些算法隨著交互記錄的數量而增加(數據集增加)。

The biggest disadvantage of collaborative filtering is that they only learn from past data points and hence suffer from the cold start problem. It’s impossible to recommend anything new (new content, new items) and challenging for items with few user interactions. In those cases, the recommender systems typically use fallback strategies such as random recommendations or most popular items.

協作過濾的最大缺點是，它們只能從過去的數據點中學習，因此會遇到冷啟動問題 。 對于幾乎沒有用戶交互的項目，不可能推薦新的東西(新內容，新項目)，也很難提出建議。 在那些情況下，推薦系統通常使用備用策略，例如隨機推薦或最受歡迎的商品。

基于內容的方法 (Content based methods)

On the other hand, content based methods use additional features and information about the users or items to learn from a model. A feature in this context simply means information about a user or item. If we consider typical user features such as age, gender or other personal information, we can learn the relationships between user details and their preferences.

另一方面，基于內容的方法使用其他功能和有關用戶或項目的信息以從模型中學習。 在此上下文中，功能僅表示有關用戶或項目的信息。 如果我們考慮典型的用戶功能(例如年齡，性別或其他個人信息)，則可以了解用戶詳細信息與其偏好之間的關系。

The same is true for additional item characteristics which help to understand commonalities or differences between items.

對于有助于理解項目之間的共性或差異的其他項目特征，也是如此。

The main idea is building a model (representation) which explains user behaviour (interactions) using additional features data.

主要思想是構建一個模型(表示形式)，該模型使用其他要素數據來解釋用戶行為(交互)。

Content based methods are less vulnerable to the cold start problem because they can use similarities in user/item characteristics to infer recommendations. This limits the cold start problems to only new users/items which also have new (unknown) features. Using a model to predict the recommendation has a cost which is described as a bias-variance tradeoff.

基于內容的方法較不容易受到冷啟動問題的影響，因為它們可以使用用戶/項目特征的相似性來推斷推薦。 這將冷啟動問題限制為僅具有新功能(未知)的新用戶/項目。 使用模型來預測推薦具有成本，該成本被描述為偏差方差折衷 。

Without explicitly explaining the implications of bias and variance, it can be understood as the compromise between model complexity and data volume. This usually requires more effort in carefully fine tuning your models.

在沒有明確解釋偏差和方差的含義的情況下，可以將其理解為模型復雜性和數據量之間的折衷。 這通常需要更多的精力來仔細地微調模型。

混合方式 (Hybrid approach)

The hybrid approach is a combination of collaborative filtering and the content based approach. One way to archive those systems is to simply have two models and then mix the recommendations from both to ensure a more robust recommendation system. The second more sophisticated way is to combine both approaches — this is often done using machine learning concepts such as neural networks.

混合方法是協作過濾和基于內容的方法的組合。 歸檔這些系統的一種方法是簡單地擁有兩個模型，然后混合來自兩個模型的推薦以確保更強大的推薦系統。 第二種更復雜的方法是將兩種方法結合起來-通常使用機器學習概念(例如神經網絡)來完成。

亞馬遜個性化 (Amazon Personalize)

AWS realised that many customers were struggling to build recommendation systems on top of their own customer data. So, they focused on solving a very common, but complex problem for their customers.

AWS意識到許多客戶都在努力根據自己的客戶數據構建推薦系統。 因此，他們專注于為客戶解決一個非常普遍但復雜的問題。

Amazon Personalize allows developers with no prior machine learning experience to easily build sophisticated personalisation capabilities into their applications, using machine learning technology by leveraging Amazon’s experience.

Amazon Personalize允許沒有先前機器學習經驗的開發人員利用機器學習技術，通過利用Amazon的經驗，輕松地在其應用程序中構建復雜的個性化功能。

Amazon Personalize supports collaborative filtering, the content based approach and a very powerful hybrid approach using hierarchical recurrent neural networks.

Amazon Personalize支持協作過濾，基于內容的方法以及使用分層遞歸神經網絡的非常強大的混合方法。

Amazon Personalize試圖解決什么？ (What is Amazon Personalize trying to solve?)

AWS realized that the end-to-end workflow for developing and deploying recommendation systems is a challenging process. If recommendation systems are built from scratch, it typically requires experts and a higher level technical maturity from an organisation to successfully deploy recommendation models in production.

AWS意識到，用于開發和部署推薦系統的端到端工作流程是一個具有挑戰性的過程。 如果推薦系統是從頭開始構建的，則通常需要專家和組織的更高技術成熟度才能在生產中成功部署推薦模型。

Amazon Personalize identifies a typical development workflow to build highly capable recommender systems. Whilst the focus is on ease of use and abstraction of complexity, the model configuration itself allows expert level access and control of model parameters. From our research so far at DiUS, we’ve found that this flexibility has great potential, whereby as ML practitioners working with our customers, we will be able to leverage the more managed aspects for some use cases but then break away and implement something more bespoke for others.

Amazon Personalize確定了典型的開發工作流程，以構建功能強大的推薦系統。 雖然重點是易用性和復雜性的抽象，但是模型配置本身允許專家級訪問和控制模型參數。 從我們在DiUS的迄今為止的研究中，我們發現這種靈活性具有巨大的潛力，借此，隨著ML從業人員與客戶合作，我們將能夠在某些用例中利用更多可管理的方面，但隨后會放棄并實現更多的功能。為他人定制。

Here are a few examples of how personalization could be used in applications:

以下是一些有關如何在應用程序中使用個性化的示例：

Personalized recommendations

個性化推薦

• Product and content recommendations tailored to a user’s profile (preferences).
  針對用戶個人資料(首選項)量身定制的產品和內容推薦。

Personalized search

個性化搜索

• Search results consider each user’s preferences.
  搜索結果考慮每個用戶的偏好。
• Intent to surface products that are relevant to the individual.
  意圖顯示與個人相關的產品。

Personalized notifications

個性化通知

• Promotions based on a user’s behaviour.
  基于用戶行為的促銷。
• Select the most appropriate mobile app notification to send based on a user’s location, buying habits and discount amounts.
  根據用戶的位置，購買習慣和折扣金額，選擇最合適的移動應用通知進行發送。

您能多快啟動并運行？ (How quickly could you get up and running?)

The answer to that question…it depends!

這個問題的答案…… 取決于！

Setting up the required AWS resources and uploading some data can be done in a couple of hours. Training models takes time, which is proportional to the amount of data provided. However, it can also be achieved within the same day. We’ve found that deploying an Amazon Personalize endpoint and testing the recommendation on top of a successful model can be done in minutes!

設置所需的AWS資源并上傳一些數據可以在幾個小時內完成。 訓練模型所花費的時間與提供的數據量成正比。 但是，也可以在同一天內完成。 我們發現，可以在幾分鐘內完成部署Amazon Personalize終端并在成功的模型之上測試建議的過程！

However, we’ve also learned that finding and using the right data for your recommendation solution is an entirely different problem.

但是，我們還了解到，為建議解決方案尋找和使用正確的數據是一個完全不同的問題。

The timeframe will be largely impacted by organisational data readiness. Which means easy access to data exports and high quality datasets. Getting data (repeatedly) in a clean format can take anywhere from a day up to weeks.

時間范圍將在很大程度上受組織數據準備就緒的影響。 這意味著輕松訪問數據導出和高質量數據集。 (重復)以干凈的格式獲取數據可能需要一天到幾周的時間。

技術概念 (Technical concepts)

This is a basic overview of the key technical concepts. For more of the technical detail, you might like to refer to the official Amazon Personalize documentation.

這是關鍵技術概念的基本概述。 有關更多技術細節，您可能希望參考官方的Amazon Personalize文檔 。

工作流程概述 (Workflow overview)

Amazon Personalize can be considered as a complete solution to build an advanced recommender system which includes the entire lifecycle of a recommendation system.

Amazon Personalize可被視為構建高級推薦系統的完整解決方案，其中包括推薦系統的整個生命周期。

The above image — from the AWS website — lists the activities involved in setting up a workflow.

上面的圖片(來自AWS網站)列出了設置工作流程所涉及的活動。

Typically, there are three main activities involved.

通常，涉及三個主要活動。

1. Data preparation

1.數據準備

• Identifying a suitable dataset
  識別合適的數據集
• Removing incorrect or augmenting missing data points
  刪除不正確或增加丟失的數據點
• Exporting data in required format
  以所需格式導出數據
• Defining a dataset schema
  定義數據集架構

2. Model training

2.模型訓練

• Selecting the appropriate solution (algorithm)
  選擇適當的解決方案(算法)
• Model configuration
  型號配置
• Model training
  模型訓練
• Model evaluation
  模型評估

3. Model deployment

3.模型部署

• Creating a model endpoint (API access to predictions)
  創建模型端點(對預測的API訪問)

Datasets and dataset groups

數據集和數據集組

Each model is dependent on the dataset group which contains the individual dataset. You can build multiple models against the same dataset and select the best option.

每個模型都取決于包含單個數據集的數據集組。 您可以針對同一數據集構建多個模型，然后選擇最佳選項。

• Relationship between dataset / solution and campaigns
  數據集/解決方案與活動之間的關系

Interaction dataset

互動數據集

• Record of interactions between user and items with a timestamp
  記錄帶有時間戳的用戶和項目之間的交互

User dataset

用戶數據集

• User specific details such as age, gender, address etc. User_ID used to map back to interactions
  用戶特定的詳細信息，例如年齡，性別，地址等。User_ID用于映射回交互

Items dataset

項目數據集

• Items details such as genre, preis, description etc. Item_ID used to map back to interaction dataset
  項目詳細信息，例如類型，風格，描述等。Item_ID用于映射回交互數據集

For more information see Amazon Personalize documentation.

有關更多信息，請參閱Amazon Personalize文檔 。

數據集架構 (Dataset schema)

Amazon Personalize is guiding the data selection process by requiring the data to conform with a predefined schema. Schemas are defined as JSON structures and will be versioned by Amazon Personalize. Each dataset schema has mandatory files which have to match the CSV column names. The mandatory fields help to map common user and item data so the model training can convert them accordingly.

Amazon Personalize通過要求數據符合預定義的架構來指導數據選擇過程。 模式定義為JSON結構，并將由Amazon Personalize進行版本控制。 每個數據集模式都有必填文件，這些文件必須與CSV列名匹配。 必填字段有助于映射普通用戶和商品數據，以便模型訓練可以相應地轉換它們。

Each dataset has some reserved keywords which you would typically use in the context of a recommendation scenario.

每個數據集都有一些保留的關鍵字 ，您通常會在推薦方案的上下文中使用這些保留的關鍵字 。

The key takeaway from the schema concept is that while there is some flexibility in defining your own schema, Amazon Personalize is asking users to convert/map data to their predefined schema. This helps users to guide data selection and also puts focus on what’s important. If you define additional fields in your user/item data, you have to decide if that data is categorical or quantitative.

模式概念的關鍵之處在于，盡管在定義自己的模式方面具有一定的靈活性，但Amazon Personalize要求用戶將數據轉換/映射到其預定義模式。 這可以幫助用戶指導數據選擇，也可以將重點放在重要的方面。 如果在用戶/項目數據中定義其他字段，則必須確定該數據是分類數據還是定量數據。

Categorical variables represent types of data which may be divided into groups. Whereas quantitative variables represent numbers which implies ordering (e.g. integer or float).

分類變量表示可以分為幾組的數據類型。 定量變量代表暗示排序的數字(例如整數或浮點數)。

食譜(又名算法) (Recipes (aka algorithms))

Amazon Personalize is offering a mixture of collaborative filtering and content based algorithms — named recipes — which can be categorised into three classes.

Amazon Personalize提供了協作式過濾和基于內容的算法(稱為食譜)的混合，可以分為三類。

用戶個性化食譜 (User Personalization Recipes)

Predict which item a user will most likely interact:

預測用戶最有可能互動的項目：

HRNN is a hierarchical recurrent neural network (hybrid approach)

HRNN是分層遞歸神經網絡(混合方法)

• HRNN
  人力資源網絡
• HRNN with metadata (user/item dataset)
  帶有元數據的HRNN(用戶/項目數據集)
• HRNN coldstart aware model
  HRNN冷啟動感知模型

Popularity-Count Recipe

人氣計數食譜

• Most popular items based on interaction count
  基于互動次數的最受歡迎商品

Personalized-Ranking Recipe (collaborative filtering)

個性化排名食譜 (協作過濾)

Product and content recommendations tailored to a user’s profile

根據用戶個人資料量身定制的產品和內容推薦

HRNN a hierarchical recurrent neural network

HRNN分層遞歸神經網絡

• filter and rerank results
  篩選并重新排序結果

Related Items Recipe

相關項目食譜

SIMS Recipe (collaborative filtering)

SIMS食譜(協作過濾)

• Item-to-item similarities (SIMS)
  項到項相似性(SIMS)

The documentation is straightforward on how to select a recipe for training a model. Amazon Personalize is following good practice by selecting sensible default configurations, but also allowing the user to go deep into tuning their models.

該文檔直接介紹了如何選擇用于訓練模型的配方。 Amazon Personalize通過選擇合理的默認配置來遵循良好做法，而且還允許用戶深入調整模型。

超參數 (Hyperparameter)

Model configuration parameters are also referred to as Hyperparameter. Those values are estimated without actually using any real data. Sometimes they are also referred to as ‘good guesses’.

模型配置參數也稱為超參數。 這些值是在沒有實際使用任何實際數據的情況下估算的。 有時，它們也被稱為“好的猜測”。

Amazon Personalize is offering an automatic tuning of these hyperparameters. Which is essentially a grid search for parameters to find the most successful configuration, this however is abstracted from the user as an optional step. Again, we like the fact that this is available but only as required given the problem at hand.

Amazon Personalize提供了這些超參數的自動調整。 從本質上講，這是對參數進行網格搜索以找到最成功的配置，但是，這是作為可選步驟從用戶中抽象出來的。 再次，我們喜歡這樣一個事實，即只有在考慮到手頭的問題時才需要這樣做。

解決方案(模型培訓) (Solutions (model training))

A solution version is the term Amazon Personalize uses for a trained machine learning model.

解決方案版本是術語Amazon Personalize用于受過訓練的機器學習模型。

The creation of a solution requires the user to select one of the recipe’s, as well as provide the required dataset and their corresponding schemas.

解決方案的創建需要用戶選擇配方之一，并提供所需的數據集及其相應的模式。

模型評估 (Model evaluation)

Amazon Personalize supports various numerical metrics to measure the model performance.

Amazon Personalize支持各種數值指標來衡量模型的性能。

Depending on the choice of recipe (algorithm) certain metrics will be generated. We are just looking at two types of metrics, however if you would like more detail, you can refer to the documentation.

根據配方(算法)的選擇，將生成某些指標。 我們僅研究兩種類型的指標，但是，如果您想了解更多詳細信息，可以參考文檔 。

precision_at_K — Is the total relevant items divided by total recommended items.

precision_at_K-相關項目總數除以建議項目總數。

normalized_discounted_cumulative_gain_at_K — Considers positional effects by applying inverse logarithmic weights based on the positions of relevant items, normalised by the largest possible scores from ideal recommendations.

normalized_discounted_cumulative_gain_at_K-通過根據相關項目的位置應用對數權重來考慮位置效應，并根據理想建議中的最大可能得分對其進行歸一化。

From our experience, recommendation is a challenging problem and typically those models have a relatively low accuracy on an individual predictions scale, however because we typically get many more opportunities to recommend, a small increase can have big impact.

根據我們的經驗，推薦是一個具有挑戰性的問題，通常這些模型在單個預測范圍內的準確性較低，但是，由于我們通常會獲得更多的推薦機會，因此少量增加可能會產生重大影響。

廣告活動(模型部署) (Campaigns (model deployment))

The creation of a campaign is packaging your solution together with some wrapping code into a HTTP endpoint. This all is done automatically by Amazon Personalize. The user has to simply select a solution model and minimum expected Transaction-per-minute TPS.

一個運動的創建與某些封裝代碼成HTTP端點一起打包的解決方案。 這一切由Amazon Personalize自動完成。 用戶只需選擇解決方案模型和最低的每分鐘預期TPS交易量即可。

Model predictions are available via HTTP or AWS SDK and can be either a single recommendation or batch predictions.

模型預測可通過HTTP或AWS開發工具包獲得，可以是單個建議或批量預測。

結論 (Conclusion)

We are now observing the rapid change in consumer behaviour in real time due a drastic impact on our environment. We were looking at the OODA Loop framework on how organisations have to analyse and react to those underlying changes.

由于對環境的巨大影響，我們現在正在實時觀察消費者行為的快速變化。 我們正在研究OODA Loop框架，以了解組織如何分析和響應那些潛在的變化。

We think that powerful recommender systems are one way for organisations to reduce their OODA loop and react quickly to rapid changes. Looking at the types of recommender systems,

我們認為，強大的推薦系統是組織減少OODA循環并快速響應快速變化的一種方法。 查看推薦系統的類型，

collaborative filtering and content based approaches helped to understand what challenges we have to solve.

協作式過濾和基于內容的方法有助于了解我們必須解決的挑戰。

Amazon Personalize is a new contender in the recommendation market and has some advantages for existing Amazon cloud customers since most of their data is already in the cloud. It’s using a state-of-the-art recommendation algorithm that addresses cold start problem.

Amazon Personalize是推薦市場中的新競爭者，并且對現有的Amazon云客戶具有一些優勢，因為他們的大多數數據已經在云中。 它使用最新的推薦算法來解決冷啟動問題 。

Amazon Personalize is trying to provide easier access to the complex world of custom recommendation systems (trained on your own customer data).

Amazon Personalize試圖提供對復雜的自定義推薦系統世界(以您自己的客戶數據進行培訓)的訪問。

Part 2 of this blog post will look into the challenges you might face when building on top of Amazon Personalize and how to automate the entire process.

這篇博客文章的第2部分將探討在Amazon Personalize之上構建時可能面臨的挑戰，以及如何使整個過程自動化。