Reinforcement learning is a machine learning technique that enables an agent to learn from its own actions and feedback in an environment. Reinforcement learning does not require labeled data or explicit rules, but rather relies on trial and error and reward and punishment mechanisms to optimize the agent's behavior and achieve a goal. Reinforcement learning can be used to solve complex and dynamic problems that involve sequential decision making and adaptation to changing situations1.
For the use case of creating an inventory prediction model for a large grocery retailer with stores in multiple regions, reinforcement learning is a suitable algorithm to use. This is because the problem involves multiple factors that affect the inventory demand, such as region, location, historical demand, and seasonal popularity, and the inventory manager needs to make optimal decisions on how much and when to order, store, and distribute the products. Reinforcement learning can help the inventory manager to learn from the new inventory data on a daily basis, and adjust the inventory policy accordingly. Reinforcement learning can also handle the uncertainty and variability of the inventory demand, and balance the trade-off between overstocking and understocking2.
The other options are not as suitable as option B, because they are not designed to handle sequential decision making and adaptation to changing situations. Option A, classification, is a machine learning technique that assigns a label to an input based on predefined categories. Classification can be used to predict the inventory demand for a single product or a single period, but it cannot optimize the inventory policy over multiple products and periods. Option C, recurrent neural networks (RNN), are a type of neural network that can process sequential data, such as text, speech, or time series. RNN can be used to model the temporal patterns and dependencies of the inventory demand, but they cannot learn from feedback and rewards. Option D, convolutional neural networks (CNN), are a type of neural network that can process spatial data, such as images, videos, or graphs. CNN can be used to extract features and patterns from the inventory data, but they cannot optimize the inventory policy over multiple actions and states. Therefore, option B, reinforcement learning, is the best answer for this question.
References:
* Reinforcement learning - Wikipedia
* Reinforcement Learning for Inventory Optimization

According to the official exam guide1, one of the skills assessed in the exam is to "design, build, and productionalize ML models to solve business challenges using Google Cloud technologies". The Speech-to-Text API2 allows you to convert audio to text by applying powerful neural network models. The Natural Language API3 enables you to analyze text and extract information about the sentiment, entities, and syntax. The Cloud Functions4 service lets you write and deploy code that runs in response to events, such as a Pub/Sub message or an HTTP request. Therefore, option B is the most efficient approach to analyze the audio files for customer sentiment, as it leverages the existing Google Cloud services and avoids unnecessary data processing and model training. The other options are not relevant or optimal for this scenario. Reference:
Professional ML Engineer Exam Guide
Speech-to-Text API
Natural Language API
Cloud Functions
Google Professional Machine Learning Certification Exam 2023
Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

ウェブ検索結果によると、RunInference API1 は Apache Beam の機能であり、機械学習推論に最適化された方法でモデルをパイプラインの一部として実行できるようにします。RunInference API は、バッチ処理、キャッシュ、モデルの再読み込みなどの機能をサポートしています。RunInference API は、TensorFlow、PyTorch、Sklearn、XGBoost、ONNX、TensorRT1 などのさまざまなフレームワークで使用できます。Dataflow2 は、Google Cloud で Apache Beam パイプラインを実行するためのフルマネージド サービスです。Dataflow は、コンピューティング リソースのプロビジョニングと管理、およびパイプラインの最適化と実行を処理します。したがって、オプション D は、モデルをラップして予測を提供する Dataflow ジョブで、watchFilePattern とともに RunInference API を使用できるため、特定のユースケースに合わせてアーキテクチャを再構成するのに最適な方法です。この方法では、モデル ファイルに変更があるたびに RunInference API が Cloud Storage バケットからモデルを自動的に再読み込みするため、予測のレイテンシとモデルの更新に必要な労力を最小限に抑えることができます1。その他のオプションは、このシナリオには関係がなく、最適でもありません。参考:
RunInference API
データフロー
Google プロフェッショナル機械学習認定試験 2023
最新の Google Professional Machine Learning Engineer 実際の無料試験問題