投稿時間:2021-12-11 08:37:48 RSSフィード2021-12-11 08:00 分まとめ(45件)

カテゴリー等	サイト名等	記事タイトル・トレンドワード等	リンクURL	頻出ワード・要約等/検索ボリューム	登録日
TECH	Engadget Japanese	原始時代の平和を取り戻せ！アクションシューティング『Cave Shooter』：発掘！スマホゲーム	https://japanese.engadget.com/cave-shooter-221035607.html	caveshooter	2021-12-10 22:10:35
TECH	Engadget Japanese	忙しい年末年始は「メモ」アプリを活用！「タグ」を使えば見返すのも簡単：iPhone Tips	https://japanese.engadget.com/iphone-tips-memos-tag-221021336.html	iphonetips	2021-12-10 22:10:21
TECH	Techable（テッカブル）	博報堂、ぬいぐるみ用ボタン型スピーカー「Pechat」に新機能「ほぼ自動おしゃべりモード」を搭載	https://techable.jp/archives/168543	pechat	2021-12-10 22:00:33
AWS	AWS Machine Learning Blog	Hierarchical Forecasting using Amazon SageMaker	https://aws.amazon.com/blogs/machine-learning/hierarchical-forecasting-using-amazon-sagemaker/	Hierarchical Forecasting using Amazon SageMakerTime series forecasting is a common problem in machine learning ML and statistics Some common day to day use cases of time series forecasting involve predicting product sales item demand component supply service tickets and all as a function of time More often than not time series data follows a hierarchical aggregation structure For example in retail …	2021-12-10 22:19:22
AWS	AWS Media Blog	Using computer vision to automate media content deduplication workflows	https://aws.amazon.com/blogs/media/using-computer-vision-to-automate-media-content-deduplication-workflows/	Using computer vision to automate media content deduplication workflowsThis blog was coauthored by Vibhav Gupta Quantiphi Noor Hassan Amazon Web Services and Liam Morrison Amazon Web Services Introduction The media and entertainment M amp E industry is undergoing a multitude of transformations driven by ever changing industry trends across the value chain from content production supply chain and broadcast to distribution These transformation initiatives are leading …	2021-12-10 22:30:42
js	JavaScriptタグが付けられた新着投稿 - Qiita	フードコートで必ず見る”アレ”を再現するWebアプリを作りました	https://qiita.com/ichii731/items/6842e413b5371aaf90fa	突然「フードコートのアプリ開発したいんですけど…」と意味不な連絡してすみませんmm殆ど使われないブルブルさせるVibrationAPI最後に端末のバイブレーションをJavaScriptで操作するAPI「VibrationAPI」を紹介します。	2021-12-11 07:49:38
Program	[全てのタグ]の新着質問一覧｜teratail（テラテイル）	Rubyで生成した画像を画面表示させたい	https://teratail.com/questions/373294?rss=all	Rubyで生成した画像を画面表示させたいRubyで生成した画像を画面表示させたいWindowsのPCで、購入時のアプリケーションと、Rubyの開発環境RubynbspxnbspwithnbspMSYSが入っています。	2021-12-11 07:06:28
Ruby	Railsタグが付けられた新着投稿 - Qiita	【Rails】自己結合関連付けでお酒の順番を表現してみた。	https://qiita.com/subaru-hello/items/ce8d02e4bde17ada0b82	本記事はRUNTEQアドベントカレンダーの日目の記事となります現在私は、一軒目で飲むお酒の順番をユーザーに提供するアプリを作成しています今回は、「お酒の順番をまとめたセット」と「お酒単品」を表すに際に学習した、「自己結合関連付け」に関してを書かせていただきます以降、一軒目で飲むお酒の順番は「酒ケジュール」という言葉で表させていただきます。	2021-12-11 07:12:55
海外TECH	Ars Technica	Amid violent threats, lawmaker ditches bill to make unvaxxed pay hospital bills	https://arstechnica.com/?p=1819776	carroll	2021-12-10 22:18:47
海外TECH	MakeUseOf	How to Customize the Scrollbar in Google Chrome With Custom Scrollbars	https://www.makeuseof.com/google-chrome-customize-scrollbar/	How to Customize the Scrollbar in Google Chrome With Custom ScrollbarsIf you use Google Chrome as your go to browser you might have looked into customization options So here s how to customize the browser s scrollbar	2021-12-10 22:30:23
海外TECH	MakeUseOf	How to Use the STAR Method to Ace Behavioral Interviews	https://www.makeuseof.com/how-to-use-star-method-ace-behavioral-interviews/	How to Use the STAR Method to Ace Behavioral InterviewsBehavioral interview questions can be difficult to answer but using the STAR method you will have a higher chance of landing the job Here s how	2021-12-10 22:16:42
海外TECH	DEV Community	10 steps to build and optimize a ML model	https://dev.to/mage_ai/10-steps-to-build-and-optimize-a-ml-model-4a3h	steps to build and optimize a ML model TLDRLet s take a look at the different steps to build a prediction model and go over the what when why and how people accomplish them StepsBelow are the steps required to solve a machine learning use case and to build a model Define the ObjectiveData GatheringData CleaningExploratory Data Analysis EDA Feature EngineeringFeature SelectionModel BuildingModel EvaluationModel OptimizationConclusion Step Define the objectiveSource Pixabay What s the objective Deciding a use case you want to predict or know more about When is the objective defined The objective is the first step which is decided based on business requirements Why is it necessary to set an objective Defining the objective sheds light on what kind of data should be gathered It also helps us in judging what kind of observations are important while doing exploratory data analysis How to define an objective An objective should be clear and precise Therefore to define a clear objective we need to follow few steps like Understand the business Eg Grocery store Identify the problem Eg Less Profits List out all the possible solutions to solve the problem Eg By increasing sales or by reducing manufacturing costs or by managing inventory etc Decide on one solution Eg managing inventory we can come to this conclusion by talking to the respective business people back and forth By following the above steps we ve clearly defined that the objective is to build a model to manage inventory in order to increase store profits Step Data GatheringSource Pexels What s Data Gathering Data Gathering is nothing but collecting the data required as per the defined objective When do we gather data Once the objective is defined we will collect data Why is Data Gathering necessary Without past data we cannot predict the future hence Data Gathering is necessary In general a dataset is created by gathering data from various resources based on the objective One of the reasons for gathering data from multiple resources is to get more accurate results i e The more the data the more accurate the results will be How is Data Gathering done Data can be collected in one of the following ways mentioned below API s like Google Amazon Twitter New York Times etc Databases like AWS GCP etc Open source Kaggle UCI Machine Learning Repositories etc Web Scraping Not recommended as often it is considered as illegal The order of Defining the objective and Data gathering steps can be changed Sometimes we will have the data handy and we need to define the objective later and sometimes we will decide the objective first and then we will gather data Step Data CleaningSource Pixabay What s Data Cleaning Data cleaning is the process of removing modifying or formatting data that is incorrect irrelevant or duplicated When to clean the data Once we have the dataset ready we will clean the data Why is data cleaning necessary Data Cleaning helps in preparing the data for Exploratory Data Analysis How to do Data Cleaning We use libraries like Pandas Numpy to do Data Cleaning and apply the following key steps to determine if we need to clean the dataset Check how many rows and columns are in the dataset Look for duplicate features by going through the meta info provided Identify Numerical and Categorical features in the gathered data and check if formatting is required or not Formatting can be something like changing data types of the features correcting the typos or removing the special characters from the data if there are any If you are working with real time data then it s recommended to save the cleaned dataset in the cloud databases before the next steps Step Exploratory Data Analysis EDA Source Pixabay What s EDA In simple terms EDA is nothing but understanding and analyzing the data by using various Statistical Measures like mean median and Visualization Techniques like Univariate Analysis Bivariate Analysis etc When to perform EDA After the data cleaning stage Once the data is cleaned we perform EDA on cleaned data Why is EDA necessary Exploratory Data Analysis is considered as the fundamental and crucial step in solving any Machine Learning use case as it helps us to identify trends or patterns in the data How to perform EDA There are Python libraries like Pandas Numpy Statsmodels Matplotlib Seaborn Plotly etc to perform Exploratory Data Analysis While doing EDA some of the basic common questions we ask are What are the independent and dependent features labels in the collected data Is the selected label dependent feature Categorical or Numerical Are there any missing values in the features variables What are the summary statistics like mean etc for Numerical features What are the summary statistics like mode etc for Categorical features Are the features variables normally distributed or skewed Are there any outliers in the features variables Which independent features are correlated with the dependent feature Is there any correlation between the independent features gt So we will try to understand the data by finding answers to the above questions both Visually by plotting graphs and Statistically hypothesis testing like normality tests When we are dealing with larger datasets then it s a bit difficult to get more insights from the data Hence at this stage we sometimes use Unsupervised learning techniques like Clustering to identify hidden groups clusters in the data which thereby helps us in understanding the data more Step Feature EngineeringSource Pixabay What s Feature Engineering A feature refers to a column in a dataset while engineering can be manipulating transforming or constructing together they re known as Feature Engineering Simply put Feature Engineering is nothing but transforming existing features or constructing new features When to do Feature Engineering Feature Engineering is done immediately after Exploratory Data Analysis EDA Why is Feature Engineering necessary Feature Engineering transforms the raw data features into features which are suitable for machine learning algorithms This step is necessary because feature engineering further helps in improving machine learning model s performance and accuracy Algorithm Algorithms are mathematical procedures applied on a given data Model Outcome of a machine learning algorithm is a generalized equation for the given data and this generalized equation is called a model How to do Feature Engineering We use libraries like Pandas Numpy Scikit learn to do Feature Engineering Feature Engineering techniques include Handling Missing ValuesHandling SkewnessTreating OutliersEncodingHandling Imbalanced dataScaling down the featuresCreating new features from the existing features Step Feature SelectionSource Pixabay What s Feature Selection Feature Selection is the process of selecting the best set of independent features or columns that are required to train a machine learning algorithm When to do Feature Selection Feature Selection is performed right after the feature engineering step Why is Feature Selection necessary Feature Selection is necessary for the following reasons Improves Machine Learning Model performance Reduces training time of machine learning algorithms Improves the generalization of the model How to do Feature Selection We use Python libraries like Statsmodels or Scikit learn to do feature selection Each of the following methods can be used for selecting the best independent features Filter methodsWrapper methodsEmbedded or intrinsic methodsIf the number of selected input features are very large probably greater than the number of rows records in the dataset then we can use Unsupervised learning techniques like Dimensionality Reduction at this stage to reduce the total number of inputs to the model Step Model BuildingSource Pixabay What s Model Building Building a machine learning model is about coming up with a generalized equation for data using machine learning algorithms Machine learning algorithms are not only used to build models but sometimes they are also used for filling missing values detecting outliers etc When should you build a model You start building immediately after feature selection with independent features Why is Model Building necessary Building a machine learning model helps businesses in predicting the future How to build a model Scikit learn is used to build machine learning models Basic Steps to create a machine learning model Create two variables to store Dependent and Independent Features separately Split the variable which stores independent features into either train validation test sets or use Cross validation techniques to split the data Train set To train the algorithmsValidation set To optimize the modelTest set To evaluate the model Cross validation techniques are used to split the data when you are working with small datasets Build a model on a training set What models can you build Machine Learning algorithms are broadly categorized into two types Supervised Unsupervised machine learning algorithms Predictive models are built using Supervised Machine Learning Algorithms The models built using supervised machine learning algorithms are known as Supervised Machine Learning Models There are two types of Supervised Machine Learning Models that can be build ーRegression models Some of the regression models are Linear Regression Decision Tree Regressor Random Forest Regressor Support Vector Regression ーClassification models Some of the classification models are Logistic Regression K Nearest Neighbors Decision Tree Classifier Support Vector Machine classifier Random Forest Classifier XGBoost Unsupervised machine learning algorithms are not used to build models rather they are used in either identifying hidden groups clusters in the data or to reduce dimensions of the data Some of the unsupervised learning algorithms are Clustering Algorithms like K means clustering etc Dimensionality Reduction Techniques like PCA etc Step ーModel EvaluationSource Pixabay What s Model Evaluation In simple model evaluation means checking how accurate the model s predictions are that is determining how well the model is behaving on train and test dataset When to evaluate the model As soon as model building is done the next step is to evaluate it Why is model evaluation necessary In general we will build many machine learning models by using different machine learning algorithms hence evaluating the model helps in choosing a model which is giving best results How to evaluate a model We use the Scikit learn library to evaluate models using evaluation metrics Metrics are divided into two categories as shown Regression Model Metrics Mean Squared Error Root Mean Squared Error Mean Absolute ErrorClassification Model Metrics Accuracy Confusion Matrix Recall Precision F Score Specificity ROC Receiver Operator Characteristics AUC Area Under Curve Step Model OptimizationSource Pixabay What s Model Optimization Most of the machine learning models have some hyperparameters which can be tuned or adjusted For example Ridge Regression has hyperparameters like regularization term similarly Decision Tree model has hyperparameters like desired depth or number of leaves in a tree The process of tuning these hyperparameters to determine the best combination of hyperparameters to increase model s performance is known as hyperparameter optimization or hyperparameter tuning When to optimize the model After calculating the Evaluation Metrics we will choose the models with the best results and then tune hyperparameters to enhance the results Why is Model Optimization necessary Optimization increases the performance of the machine learning models which in turn increases the accuracy of the models and gives best predictions How to do Model Optimization We make use of libraries like Scikit learn etc or we can use frameworks like Optuna to optimize by tuning hyperparameters Hyperparameter tuning approaches include Grid SearchRandom SearchBayesian OptimizationGenetic Algorithms Step ConclusionSource PixabayFinally we will choose our hyperparameter optimized model with the best metrics and use that model for production After all these steps if you are still not happy with the machine learning model s performance then you can repeat the entire process starting from Step through Step Remember Machine Learning is an iterative hit and trial process and its performance also depends on the sample of the data we gathered That s it for this blog I tried my best to keep it as simple as possible and I hope you all got an idea on how to build and optimize a machine learning model As part of this series we will implement all the above mentioned steps on Telco Customer data and come up with the best model to predict whether a customer churns Thanks for reading This guest blog was written by Jaanvi Learn more about her on LinkedIn	2021-12-10 22:34:14
海外TECH	Engadget	Mercedes-Benz recalls EQS over error that allowed dashboard video playback while driving	https://www.engadget.com/mercedes-benz-mbux-server-side-configuration-error-224912962.html?src=rss	Mercedes Benz recalls EQS over error that allowed dashboard video playback while drivingMercedes Benz has issued a server side update to fix an oversight that had allowed owners of its EQS EV and recent S Class sedans to watch video content on the inch MBUX Hyperscreen displays found in those cars while they were in motion In a National Highway Traffic Safety Administration filing spotted by Consumer Reports editor Keith Barry the automaker says it found an “incorrect configuration on its backend server in November that may have been installed on some vehicles It estimates nearly cars were affected by the oversight And while Mercedes is not aware of any crashes it s moving forward with a recall News of the decision comes in the same week that a report from The New York Times said Tesla recently updated its vehicles to allow passengers to play select games even while their car was moving “Solitaire is a game for everyone but playing while the car is in motion is only for passengers the company s infotainment system says after someone launches the title It s possible for the driver to bypass that warning and then play the game It s a feature NHTSA says it s in contact with Tesla about “The Vehicle Safety Act prohibits manufacturers from selling vehicles with design defects posing unreasonable risks to safety a spokesperson for the agency told Engadget In NHTSA said people in the US died in crashes involving distracted drivers	2021-12-10 22:49:12
海外科学	NYT > Science	Who Can Be Called an Astronaut? The F.A.A. Will No Longer Say.	https://www.nytimes.com/2021/12/10/science/astronaut-wings-faa-bezos-musk.html	honor	2021-12-10 22:50:51
金融	金融総合：経済レポート一覧	暗号資産「取引所仮想通貨」の衝撃～なぜ「暗号資産取引所」は自ら暗号資産を発行するのか：Watching	http://www3.keizaireport.com/report.php/RID/477901/?rss	watching	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	FX Daily(12月9日)～ドル円、113円台前半まで下落	http://www3.keizaireport.com/report.php/RID/477903/?rss	fxdaily	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	景気予測調査から見た今期業績見通し～鉱工業を中心に増収・増益幅拡大：Economic Trends	http://www3.keizaireport.com/report.php/RID/477906/?rss	economictrends	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	工作機械受注が教えてくれる景況感～ピークアウト：Market Flash	http://www3.keizaireport.com/report.php/RID/477908/?rss	marketflash	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	ターゲット・デート・ファンドは十分なインフレ対抗策になるか?：マルチアセット	http://www3.keizaireport.com/report.php/RID/477911/?rss	発表	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	日銀のコロナオペは延長へ～日本銀行の本格的な政策変更の可能性は考えられない...：木内登英のGlobal Economy ＆ Policy Insight	http://www3.keizaireport.com/report.php/RID/477917/?rss	lobaleconomypolicyinsight	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	貸出・マネタリー統計（21年11月）～銀行貸出は伸び悩み、対面サービス業向けもじわりと減少：経済・金融フラッシュ	http://www3.keizaireport.com/report.php/RID/477920/?rss	銀行	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	「共同富裕」を目指す中国の未来：株式	http://www3.keizaireport.com/report.php/RID/477923/?rss	発表	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	株式市場の見通し： 不透明性を乗り切るアクティブ運用：株式	http://www3.keizaireport.com/report.php/RID/477924/?rss	株式市場	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	役員報酬制度にESGを組み入れる：責任投資	http://www3.keizaireport.com/report.php/RID/477925/?rss	役員報酬	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	コロナ禍における銀行券の動向：日銀レビュー	http://www3.keizaireport.com/report.php/RID/477936/?rss	日本銀行	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	通貨及び金融の調節に関する報告書（2021年12月）その1	http://www3.keizaireport.com/report.php/RID/477940/?rss	日本銀行	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	通貨及び金融の調節に関する報告書（2021年12月）その2	http://www3.keizaireport.com/report.php/RID/477941/?rss	日本銀行	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	通貨及び金融の調節に関する報告書（2021年12月）その3	http://www3.keizaireport.com/report.php/RID/477942/?rss	日本銀行	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	温暖化対策の移行金融、国際原則は2023年までに策定～金融機関のDX対応、規制緩和・インフラ整備で促進：デジタル社会研究会 議事要旨（第21回）	http://www3.keizaireport.com/report.php/RID/477949/?rss	日本経済研究センター	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	INCLUSIVE（東証マザーズ）～メディア運営企業や事業会社のインターネットサービスの拡大と収益化を支援。22年3月期上期は費用の増加により営業損失を計上したが通期の黒字化を見込む：アナリストレポート	http://www3.keizaireport.com/report.php/RID/477951/?rss	inclusive	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	ツクイスタッフ（東証JASDAQ）～介護・医療業界に特化して全国展開する人材サービス企業。コロナ感染症の影響の軽減や新たな施策の効果により、中期的な業績回復を予想：アナリストレポート	http://www3.keizaireport.com/report.php/RID/477952/?rss	jasdaq	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	TCFDが基準の一部改訂とガイダンスを公表～気候関連の指標、目標、低炭素経済への移行計画に係る開示の解説：ESG投資	http://www3.keizaireport.com/report.php/RID/477954/?rss	大和総研	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	事業性評価におけるクラウドファンディング活用の可能性について	http://www3.keizaireport.com/report.php/RID/477956/?rss	商工総合研究所	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	週刊！投資環境（2021年12月10日号）～来週の注目点を皆さまにいち早くお届け...	http://www3.keizaireport.com/report.php/RID/477960/?rss	投資信託	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	【注目検索キーワード】リベンジ消費	http://search.keizaireport.com/search.php/-/keyword=リベンジ消費/?rss	検索キーワード	2021-12-11 00:00:00
金融	金融総合：経済レポート一覧	【お薦め書籍】なぜウチの会社は変われないんだ! と悩んだら読む 大企業ハック大全	https://www.amazon.co.jp/exec/obidos/ASIN/4478114196/keizaireport-22/	選抜	2021-12-11 00:00:00
金融	ニュース - 保険市場TIMES	東京海上日動、ドライブレコーダーを活用した人命救助の仕組み構築	https://www.hokende.com/news/blog/entry/2021/12/11/080000	東京海上日動、ドライブレコーダーを活用した人命救助の仕組み構築年度中の導入を目指す東京海上日動火災保険株式会社以下、東京海上日動は、認定NPO法人救急ヘリ病院ネットワークおよび株式会社プレミア・エイドと連携して、ドライブレコーダーを活用した人命救助の仕組み「第種DCallNet」を構築し、年度中の導入を目指すと発表した。	2021-12-11 08:00:00
ニュース	BBC News - Home	Late goals give Brentford dramatic comeback win over Watford	https://www.bbc.co.uk/sport/football/59514682?at_medium=RSS&at_campaign=KARANGA	community	2021-12-10 22:19:09
ニュース	BBC News - Home	Racing 92 saunter to five-try win over Northampton	https://www.bbc.co.uk/sport/rugby-union/59596740?at_medium=RSS&at_campaign=KARANGA	opener	2021-12-10 22:20:54
ニュース	BBC News - Home	Rangnick will not try to convince Pogba to sign new deal	https://www.bbc.co.uk/sport/football/59615527?at_medium=RSS&at_campaign=KARANGA	manchester	2021-12-10 22:38:29
ビジネス	ダイヤモンド・オンライン - 新着記事	米インフレ高進、FRBテーパリング加速を後押し - WSJ発	https://diamond.jp/articles/-/290389	後押し	2021-12-11 07:20:00
北海道	北海道新聞	首相、盟友登用が裏目に　石原内閣参与辞任	https://www.hokkaido-np.co.jp/article/621702/	内閣官房参与	2021-12-11 07:18:05
北海道	北海道新聞	道内マグロ漁獲枠３１９トン　水産庁の配分案　来年９％増	https://www.hokkaido-np.co.jp/article/621703/	配分	2021-12-11 07:15:28
北海道	北海道新聞	オミクロン拡大　年末年始の人流増警戒　道内第６波招く可能性	https://www.hokkaido-np.co.jp/article/621714/	年末年始	2021-12-11 07:10:31
ビジネス	東洋経済オンライン	2022年｢生活が苦しくなる悪い円安｣にはならない 黒字を稼ぐ日本経済の｢底力｣は健在なり！ | 新競馬好きエコノミストの市場深読み劇場 | 東洋経済オンライン	https://toyokeizai.net/articles/-/475694?utm_source=rss&utm_medium=http&utm_campaign=link_back	一般社団法人	2021-12-11 07:30:00