自動機械学習とは

自動機械学習とは、DataRobot が開発したテクノロジであり、人工知能(AI)アプリケーションや機械学習アプリケーションの開発に必要な多くの作業を自動化します。DataRobot には世界トップクラスのデータサイエンティストの専門知識が組み込まれています。DataRobot を活用することで、社内のユーザーはデータやビジネスに関する知識を活用し、残りの作業を DataRobot に任せることができます。

自動機械学習が必要な理由

自動機械学習は、人間とコンピュータ両方の強みを活用します。人間は、コミュニケーションやエンゲージメント、コンテキスト、一般的な知識、さらに創造性や共感性という点で優れています。コンピュータやソフトウェアシステムは、反復的な作業、演算、データ操作、並列処理に最適であり、複雑なソリューションをやり遂げる性能と速度を提供します。

簡単に言うと、自動機械学習とは次のようなものです。
エキスパートと同等のシステム
世界トップクラスのデータサイエンティストが生み出したベストプラクティスを取り入れることで、最良の機械学習アルゴリズムを自動的に選択し、データや現在のビジネス上の課題に対してテストを行います。
信頼性
機械学習アルゴリズムが決定を下す方法や、データからパターンの変化が推定された場合にモデルを再トレーニングする方法について、人間にとってわかりやすく、簡単に解釈できる説明を提供します。

自動機械学習は、高度な機械学習モデルを構築する力を備えた新しい「シチズンデータサイエンティスト」を生み出します。コーディングを習得したり、特定のアルゴリズムをいつどのように適用すべきかを理解したりする必要はありません。また、モデル構築プロセスでの反復的な手順が自動化されるため、データサイエンティストの生産性が向上し、モデルの選定や微調整に専門知識を活用できるようになります。

自動機械学習の 10 のステップ

自動機械学習は、従来のデータサイエンスプロセスで必要となる手作業の大部分を置き換えますが、完全に自動化された機械学習ソリューションとなるには、次の主な要件をすべて満たしている必要があります。DataRobot は、機械学習モデルの構築と配備を効果的に自動化するために必要となる 10 のステップすべてに対応する業界初で唯一の機械学習プラットフォームです。

1 2 3 4 5 6 7 8 9 10

データの準備

特徴量エンジニアリング

多様なアルゴリズム

アルゴリズムの選択

トレーニングとチューニング

アンサンブル

一対一のモデル比較

人間にわかりやすいインサイト

容易な配備

モデルの監視と管理

ステップ1:

データの準備

Every machine learning algorithm works differently and has different data requirements. For example, some algorithms need numeric features to be normalized, and some do not. DataRobot transforms raw data into the specific format that each algorithm needs for optimal performance then follows best practices for data partitioning.

How Do Model Blueprints Add Value to DataRobot?

ステップ2:

特徴量エンジニアリング

Feature engineering is the process of modifying data to help machine learning algorithms work better, and is often time-consuming and expensive. DataRobot engineers new features from existing numeric, categorical, and text features. It knows which algorithms benefit from extra feature engineering and which don’t, and only generates features that make sense given the data characteristics.

Automated Feature Engineering

ステップ3:

多様なアルゴリズム

Every dataset contains unique information that reflects the individual characteristics of a business. Due to the variety of situations and conditions, one algorithm cannot successfully solve every possible business problem or dataset. With DataRobot you get immediate access to hundreds of diverse algorithms, and the appropriate pre-processing, to test against your data in order to find the best one for your particular AI challenge.

AIs are Individuals, Just Like People

ステップ4:

アルゴリズムの選択

Having hundreds of algorithms at your fingertips is great, but in many cases users don’t have time to try each and every algorithm on their data. Some algorithms aren’t suited to the data, some are not suited to the data sizes, and some are extremely unlikely to work well on the data. DataRobot will only run the algorithms that make sense for your data.

Can An AI Recommend the Best Algorithm for Me?

ステップ5:

トレーニングとチューニング

It’s standard for machine learning software to train the model on your data. DataRobot takes this a step further by using smart hyperparameter tuning, not just brute force, to tune the most important hyperparameters for each algorithm. The platform knows which features to include and which to leave out, and which feature selection method works best for different algorithms.

ステップ6:

アンサンブル

In data science jargon, teams of algorithms voting together on an estimated outcome are called “ensembles” or “blenders.” Each algorithm’s strengths balance out the weaknesses of another. Ensemble models typically outperform individual algorithms because of their diversity. DataRobot finds the optimal algorithms to blend together and tunes the weighting of the algorithms within each blender model.

ステップ7:

一対一のモデル比較

You won’t know in advance which algorithm will perform the best, so you need to compare the accuracy and speed of different algorithms on your data regardless of which programming language or machine learning library they came from. You can think of it as a competition amongst the models where the best model wins! DataRobot builds and trains dozens of models, compares the results, and ranks the models by accuracy, speed, and the most efficient combination of the two.

Competition in AI Blog

ステップ8:

人間にわかりやすいインサイト

Over the past few years, machine learning and AI have made massive strides in predictive power, but at the price of complexity. It is not enough for a model to score well on accuracy and speed – you also have to trust the answers it is giving. And in regulated industries, you must justify the model to a regulator. DataRobot explains model decisions in a human-interpretable manner, showing which features have the greatest impact on the accuracy of each model and the patterns fitted for each feature. DataRobot can also provide prediction explanations to illustrate the key reasons why a specific prediction was made.

Give me one good reason to trust artificial intelligence

ステップ9:

容易な配備

A recent Harvard Business Review article described a team of analysts that built an impressive predictive model, but the business lacked the infrastructure needed to directly implement the trained model in a production setting, which was a waste of time and resources. All DataRobot models are production-ready, and can be deployed in several ways on standard system hardware. DataRobot offers AI Services and its technical support teams are located around the world to assist with model building and deployment, 24 hours per day.

Model Deployment with DataRobot

ステップ10:

モデルの監視と管理

In a constantly changing world, your AI applications need to keep up to date with the latest trends. DataRobot makes it easy to compare predictions to actual results and to train a new model on the latest data. DataRobot also proactively identifies when a model’s performance is deteriorating over time.

What’s Model Risk and Why Does it Matter?

ステップ 1: データの準備

Every machine learning algorithm works differently and has different data requirements. For example, some algorithms need numeric features to be normalized, and some do not. DataRobot transforms raw data into the specific format that each algorithm needs for optimal performance then follows best practices for data partitioning.

How Do Model Blueprints Add Value to DataRobot?

ステップ 2: 特徴量エンジニアリング

Feature engineering is the process of modifying data to help machine learning algorithms work better, and is often time-consuming and expensive. DataRobot engineers new features from existing numeric, categorical, and text features. It knows which algorithms benefit from extra feature engineering and which don’t, and only generates features that make sense given the data characteristics.

Automated Feature Engineering

ステップ 3: 多様なアルゴリズム

Every dataset contains unique information that reflects the individual characteristics of a business. Due to the variety of situations and conditions, one algorithm cannot successfully solve every possible business problem or dataset. With DataRobot you get immediate access to hundreds of diverse algorithms, and the appropriate pre-processing, to test against your data in order to find the best one for your particular AI challenge.

AIs are Individuals, Just Like People

ステップ 4: アルゴリズムの選択

Having hundreds of algorithms at your fingertips is great, but in many cases users don’t have time to try each and every algorithm on their data. Some algorithms aren’t suited to the data, some are not suited to the data sizes, and some are extremely unlikely to work well on the data. DataRobot will only run the algorithms that make sense for your data.

Can An AI Recommend the Best Algorithm for Me?

ステップ 5: トレーニングとチューニング

It’s standard for machine learning software to train the model on your data. DataRobot takes this a step further by using smart hyperparameter tuning, not just brute force, to tune the most important hyperparameters for each algorithm. The platform knows which features to include and which to leave out, and which feature selection method works best for different algorithms.

ステップ 6: アンサンブル

In data science jargon, teams of algorithms voting together on an estimated outcome are called “ensembles” or “blenders.” Each algorithm’s strengths balance out the weaknesses of another. Ensemble models typically outperform individual algorithms because of their diversity. DataRobot finds the optimal algorithms to blend together and tunes the weighting of the algorithms within each blender model.

ステップ 7: 一対一のモデル比較

You won’t know in advance which algorithm will perform the best, so you need to compare the accuracy and speed of different algorithms on your data regardless of which programming language or machine learning library they came from. You can think of it as a competition amongst the models where the best model wins! DataRobot builds and trains dozens of models, compares the results, and ranks the models by accuracy, speed, and the most efficient combination of the two.

Competition in AI Blog

ステップ 8: 人間にわかりやすいインサイト

Over the past few years, machine learning and AI have made massive strides in predictive power, but at the price of complexity. It is not enough for a model to score well on accuracy and speed – you also have to trust the answers it is giving. And in regulated industries, you must justify the model to a regulator. DataRobot explains model decisions in a human-interpretable manner, showing which features have the greatest impact on the accuracy of each model and the patterns fitted for each feature. DataRobot can also provide prediction explanations to illustrate the key reasons why a specific prediction was made.

Give me one good reason to trust artificial intelligence

ステップ 9: 容易な配備

A recent Harvard Business Review article described a team of analysts that built an impressive predictive model, but the business lacked the infrastructure needed to directly implement the trained model in a production setting, which was a waste of time and resources. All DataRobot models are production-ready, and can be deployed in several ways on standard system hardware. DataRobot offers AI Services and its technical support teams are located around the world to assist with model building and deployment, 24 hours per day.

Model Deployment with DataRobot

ステップ 10: モデルの監視と管理

In a constantly changing world, your AI applications need to keep up to date with the latest trends. DataRobot makes it easy to compare predictions to actual results and to train a new model on the latest data. DataRobot also proactively identifies when a model’s performance is deteriorating over time.

What’s Model Risk and Why Does it Matter?

自動機械学習を組織全体に役立てる

データサイエンティストを探し出して雇い続けることが、企業に AI と機械学習を導入するうえで最も難しい課題となる場合があります。自動機械学習を使用すれば、ビジネスアナリストやソフトウェアエンジニアが予測モデルを構築してアプリケーションに AI を組み入れることが可能になり、既存のデータサイエンティストは生産性を向上させることができるだけでなくやりがいのある作業に集中できます。
分析の専門家

分析の専門家

実用的なハンズオントレーニングと DataRobot のワールドクラスのチームのサポートにより、ビジネス分析の専門家が短期間で AI アナリストに変わり、ビジネスの真価を高める要素を探し出してそこに集中できるようになります。

ソフトウェアエンジニア

ソフトウェアエンジニア

ソフトウェアエンジニアは、機械学習モデルを本稼働システムに統合することで、モデルの価値を高めるために重要な役割を果たします。DataRobot は、ソフトウェアエンジニアが AI エンジニアになるために必要なトレーニング、ツール、サポートを提供します。

データサイエンティスト

データサイエンティスト

データの分割、モデルのチューニング、特徴量の選択など、モデル開発に関わる日常的な作業を自動化すれば、熟練のデータサイエンティストは従来の手作業でコーディングするアプローチを遥かに凌ぐ成果を上げることができます。DataRobot は、必要に応じてモデルをカスタマイズする柔軟性も提供します。

エグゼクティブ

エグゼクティブ

ビジネスリーダーが AI の重要性を理解しており、機械学習プロジェクトについてチームに語り、枠組みを作る方法を知っていれば、専門分野に関するすべての知識と経験を会社による AI アプリケーションの構築に活かすことができます。

DataRobot がモデル構築を変革

アルゴリズムのエコシステムの絶え間ない進化についていくのがこれまでになく簡単に

With DataRobot
Old way

どのようなプロジェクトでDataRobotの導入を検討していますか?

お問い合わせ