Unlock a world of possibilities! Login now and discover the exclusive benefits awaiting you.
Forums for Qlik Analytic solutions. Ask questions, join discussions, find solutions, and access documentation and resources.
Forums for Qlik Data Integration solutions. Ask questions, join discussions, find solutions, and access documentation and resources
Qlik Gallery is meant to encourage Qlikkies everywhere to share their progress – from a first Qlik app – to a favorite Qlik app – and everything in-between.
Get started on Qlik Community, find How-To documents, and join general non-product related discussions.
Direct links to other resources within the Qlik ecosystem. We suggest you bookmark this page.
Qlik gives qualified university students, educators, and researchers free Qlik software and resources to prepare students for the data-driven workplace.
標準と詳細モードとの切替がなくなりました。値を選択したり、ソーステーブルを表示して確認しながら開発することができます。
新しいストレート テーブルが標準チャートに昇格
Visualization bundle に含まれていたストレートテーブルが標準チャートに昇格しました。これまでのテーブルは(リタイア済み)と表示されていますが、今後廃止が予定されています。廃止は十分な期間を取って事前に告知されますが、早めの移行をお勧めします。
既存のテーブルの上に、ストレートテーブルをドラッグアンドドロップして、「以下に変換」を選択するとストレートテーブルに変換することができます。完全に機能が同じではないので、念のためシートのバックアップをとってから実施してください。
ピボット テーブル インジケーター
Visualization bundle のピボットテーブルのメジャーに、インジケーターを表示できるようになりました。テーブルやストレートテーブルと同様に、限度を設定してアイコンや色を設定することができます。
データ準備のアップデート
Qlik Automate に関するアップデート
これまで個人スペースでのみ作成していた自動化を共有スペースで作成し実行することができるようになりました。これによりチームによるコラボレーションと実行を効率的に行うことができます。詳細については、「共有自動化の導入」を参照してください。
その他、使いやすさも改善されています。
Qlik Predict に関するアップデート
MLの展開で、予測ファイルに名前を付ける時に、フォルダパスも含めることができるようになりました。
レポートに関するアップデート
アプリ内のHTMLエディタを使用して、HTMLレポートを作成することができるようになりました。レポートは EメールやWebサイトに埋め込むことができます。
データ移動・変換に関するアップデート
プロジェクトをインポートしたり、変更を取り込んだり、既存のプロジェクトをバージョン管理で取得したりする際、新しいユーザー・インターフェースで、これにより、以下のようなプロジェクト設定の選択が可能になりました。
★エクスポートファイルの形式が、単一のJSONファイルから、複数のJSONファイルを含むZIPファイルに変更されました。 旧JSON形式は、2026年1月30日までインポートに対応します。 JSONファイルを新しいフォーマットに変換するには、それらを インポートし、新しいZIPフォーマットにエクスポートする必要があります。 旧JSON形式のプロジェクトは、API経由でインポートすることはできません。 2026年1月30日までに、既存のプロジェクトを新しいフォーマットにエクスポートすることをお勧めします。
SSH トンネルを使用したデータ ソースへのセキュアなアクセス
Data Movement gateway を使用せず、SSH トンネル経由でサポートされているデータ ソースに接続できるようになりました。トンネル化により、ファイアウォール内のデータ ソースに安全にアクセスすると同時に、トンネルを通過するすべてのデータを暗号化することができます。
サポートされるデータ ソース コネクタ:
カタログに関するアップデート
Developer ロールと API キーの切り替えは非推奨
「管理>ユーザーの管理>権限」の「Developer」ロールは廃止され、2025年末までに削除されます。影響を受けるユーザーとグループを「APIキーの管理」権限を含むカスタムロールに移行するか、「User Default」の「機能とアクション」の「開発者」欄で、APIキーを管理の権限を有効にしてください。
詳しくは、「カスタムロールの管理」をご覧ください。
オンプレミスで開発したアプリの評価
もともとオンプレミスで開発されたQlik Senseアプリのパフォーマンスを、 Qlik Cloudテナント内で直接評価できるようになりました。移行前やハイブリッド環境でのアプリのテスト、最適化、ベンチマークが可能になり、クラウドへの移行がよりスムーズとなります。
We’re continuing to expand the connectivity of Qlik Talend Cloud with the addition of more applications that can now be used as a data source. These connectors will help companies eliminate the lengthy development time associated with custom connectors as well as accelerate user access to a wider variety of sources. The new connectors are for:
The Qlik Data Gateway - Direct Access allows Qlik Sense SaaS applications to securely access behind the firewall data, over a strictly outbound, encrypted, and mutually authenticated connection.
We recently released Direct Access gateway 1.7.4 & 1.7.5 which, in addition to several bug fixes, introduced the following enhancements:
We have expanded our support for SAP by integrating the SAP Report Connector within Qlik Cloud Analytics, providing seamless connectivity to SAP Report objects.
git clone https://github.com/qlik-demo-team/qlik-engine-tutorial my-qlik-app
cd my-qlik-app
npm install
npm run dev
Go to http://localhost:8080 to see "My Amazing Qlik Sense Mashup!" on your screen. Note: to see the final result of any one section, you can switch to one of five branches in the repo: start (setup), connection (connecting to Qlik Sense), hypercube (getting data), list-object (making a selection), finished (completed project).
const enigma = require('enigma.js');
const schema = require('enigma.js/schemas/12.170.2.json');
const SenseUtilities = require('enigma.js/sense-utilities');
const config = {
host: '', // <== Qlik server domain here
secure: true,
port: 443,
prefix: '',
appId: '', // <== app ID here
};
const url = SenseUtilities.buildUrl(config);
const qDocPromise = enigma.create({ schema, url }).open().then(global => global.openDoc(config.appId));
console.log(qDocPromise)
Enigma.js is a Promise-based library so as you'll notice, in your console, it says Promise {<pending>} meaning it has just logged the Promise itself, not the object. Establishing the connection is a great first step in understanding how Enigma works and how we'll be communicating with our Qlik server.
qDocPromise.then((doc) => {
console.log(doc);
})
The resulting object is what we'll use to do most of the talking to the Qlik Sense server. Without going into much further detail, this object is called the "Doc" (in older versions, it was called the App but is now usually just called the Doc).
qDocPromise.then((doc) => {
console.log(doc);
doc.createSessionObject({ qInfo: { qType: 'fields' }, qFieldListDef: {}}).then((fields) => fields.getLayout().then((layout) => {
const { qItems } = layout.qFieldList;
const sorted = qItems.sort((a,b) => a.qName > b.qName ? 1 : -1)
console.log(sorted)
}))
})
If you open your console, you can see that the resulting array has of over 200 fields. Building a mashup without understanding anything about the data is difficult but the above snippet does a good job of just listing all the fields
// hypercube.js
const hypercube = {
qInfo: { qId: 'Consumer Sales', qType: 'data' },
qHyperCubeDef: {
qDimensions: [
{ qDef: { qFieldDefs: ['[Product Group Desc]']}, qFieldLabels: ['Product Group'] }
],
qMeasures: [
{ qDef: { qDef: '=SUM([Sales Margin Amount])/SUM([Sales Amount])', qLabel: 'Margin' }},
],
qInitialDataFetch: [{
qTop: 0, qLeft: 0, qWidth: 10, qHeight: 1000,
}],
qInterColumnSortOrder: [],
qSuppressZero: true,
qSuppressMissing: true,
}
}
export default hypercube;
Now that we have our hypercube, let's use our doc object to get the data. First import the hypercube at the top of the file, just below your Enigma imports, and then add the following code:
// Enigma.js imports
import hypercube from './hypercube';
// CODE
qDocPromise.then((doc) => {
// new code
doc.createSessionObject(hypercube).then((obj) => obj.getLayout().then(layout => {
console.log(layout);
const dataPages = layout.qHyperCube.qDataPages[0].qMatrix
console.log(dataPages)
}))
})
Boom! And just like that, we now have some data! In your console, you'll be able to see both the layout object as well as the data. For some users, this is good enough - if you know the fields you want, you can make as many hypercubes as you'd like to get the data you're looking for. From here, you can use vanilla JavaScript to clean-up
// listObject.js
const listObject = {
title: "A list object",
description: "Description of the list object",
qInfo: { qId: 'Consumer Sales List Object', qType: 'List Object'},
qListObjectDef: {
qStateName: "$",
qDef: { qFieldDefs: ['[Product Group Desc]'], qFieldLabels: ["Product Description"], qSortCriterias: [{qSortByLoadOrder: 1}]},
qInitialDataFetch: [{
qTop: 0, qLeft: 0, qWidth: 10, qHeight: 1000,
}],
},
}
export default listObject;
// top of page, below other import statements
import listObject from './listObject';
// CODE
qDocPromise.then((doc) => {
// Getting data from hypercube
doc.createSessionObject(hypercube).then((obj) => obj.getLayout().then(layout => {
console.log(layout);
const dataPages = layout.qHyperCube.qDataPages[0].qMatrix
console.log(dataPages)
}))
// NEW CODE: List Object
doc.createSessionObject(listObject).then((obj) => {
obj.getListObjectData('/qListObjectDef',[ {qLeft: 0, qTop: 0, qWidth: 10, qHeight: 100}]).then(objectData => {
console.log(objectData);
})
})
})
If we open our console and peak inside objectData, we see that inside the qMatrix property, there is an array with 17 items. Each item is an array with a single object that represents a possible value for the field of "Product Group Desc". There is a descriptor/title/name for that field (qText), a numeric value (qNum), an element number (qElemNumber), and it's selection state (qState). Let's try making a selection. Just for fun, let's pick "Beverages", which as we can see in the picture below has a qElemNumber of 2.
qDocPromise.then((doc) => {
// Getting data from hypercube
doc.createSessionObject(hypercube).then((obj) => obj.getLayout().then(layout => {
console.log(layout);
const dataPages = layout.qHyperCube.qDataPages[0].qMatrix
console.log(dataPages)
}))
// UPDATED CODE: List Object
doc.createSessionObject(listObject).then((obj) => {
obj.getListObjectData('/qListObjectDef',[ {qLeft: 0, qTop: 0, qWidth: 10, qHeight: 100}]).then(objectData => {
console.log(objectData);
obj.selectListObjectValues('/qListObjectDef', [2], true, false).then((res) => {
console.log(res);
obj.getListObjectData('/qListObjectDef',[ {qLeft: 0, qTop: 0, qWidth: 10, qHeight: 100}]).then(objectData2 => {
console.log(objectData2)
})
})
})
})
})
なんだ今回棒チャートか、と思った人いませんか?「基本のき」の棒チャートも工夫次第でいろんなアレンジができるんですよ。
デフォルトの設定で棒チャートを作成するとこんな感じですね。
プロパティパネルのスタイルのプレゼンテーションで「垂直」か「水平」かを切り替えられますね。
さらにスタイル指定のチャートタブで、枠線や棒の太さを変更すると下記のように見栄えを変えることができます。
続いて次は色にグラデーションを設定した例です。
左は色の設定を「カスタム 数式を使用」にして、ColorMix1を使ってピンクからベージュへのグラデーションを設定しています。
Colormix1() は、0 ~ 1 の間の値を基準に 2 色グラデーションの ARGB カラー表現を返す数式で使用されます。Colormix1 (Value , ColorZero , ColorOne)と書きます。Value は、0 と 1 の間の実数です。Value = 0 の場合、ColorZero が返され、Value = 1 の場合、ColorOne が返されます。0 < Value < 1 のとき、相当する中間の色を返します。
上記の式では案件金額の順位をRank関数で求め、それを値の数の6で割ることで 0 ~ 1 に変換して Value として使用しています。
右の例では色は同じですが、透明度をグラデーションで変更しています。ARGB関数の最初の値は透明度を示しています。続く3つの値でRGBを指定します。
次は全体で100%になる積み上げ棒チャートをアレンジしてみました。
左のあみだくじのようなチャートは色は単色とし、枠線を「大」にして棒の太さも太くして視覚的な効果を出しています。このチャートには軸が二つあります。例えば部門と四半期などです。そしてメジャーには、計算値を二つ目の軸を無視した合計「sum(Total <一つ目の軸> 項目)」で割って割合を求めています。
そして右のチャートですが、こちらは最大の値に対する各軸の比率を濃い色で表しています。実は棒チャートではなくコンボチャートで作っています。濃い色の部分は単純に項目の集計ですが、薄い透明な部分は最大の値からそれぞれの軸の値をマイナスして求めています。
この例では、軸(部門名)を無視して全部門のうち、案件金額の集計の最大値の部門の値から、各軸の案件金額をマイナスしています。
そしてコンボチャートではメジャー別にスタイルを設定することができるので、それぞれの「その他のプロパティ」でどちらも主軸とし、異なる色を設定しています。最大案件金額の透明度を上げた設定にしています。
最後に下記の2つのチャートをご覧ください。
左は棒チャートのバタフライモードです。メジャーが2つある場合にプレゼンテーションで簡単にバタフライ表示をすることができます。
右は実はコンボチャートです。2つ目のメジャーをマイナス値に変換するとともに、メジャー別のスタイル指定で色の透明度を上げた設定をしています。水に映っているような効果がありますね。
基本チャートもアイデア次第で魅力的に変身させることができます。
Happy Dueling !
** 過去の記事 **
Edited 1st of December 2025: End of Life date changed from December 31st, 2025, to January 31st, 2026.
The old versions 1.4.x and 1.5.x of Qlik Data Gateway - Direct Access will be officially End of Life by January 31st, 2026.
Both versions will stop working after reaching End of Life. We recommend you plan to upgrade to the latest available version of the currently supported 1.7.x as soon as possible.
For the upgrade procedure, please refer to Upgrading Qlik Data Gateway - Direct Access on Qlik's online help. This page also lists all the significant changes for each version.
The upgrade to 1.7.x from 1.4 or 1.5 has been thoroughly tested, and the process is expected to be smooth. However, please follow the steps carefully and always take a backup before upgrading. It is also worth noting that .NET 8.x is required (from v1.6.6) and will be automatically installed during the upgrade.
There are several configuration settings added in later versions of the Direct Access gateway that may be applicable for your deployment. Therefore, please review all details in the online help on Configuring and troubleshooting Qlik Data Gateway - Direct Access. Note that most Direct Access gateway settings can be configured in the Qlik Cloud Administration activity center (from v1.7.2).
Always upgrade to the latest version!
Version 1.6, which was initially released in December 2023, reached end-of-support on June 14, 2025, and is tentatively set for End-of-Life by end of June 2026. We will share an update later this year with the exact End-of-Life date for this version.
Please note that you are always better off upgrading to the latest version available, especially as cloud-side fixes, which get deployed almost every week, most often does not apply to older gateway versions.
If you have questions or need additional assistance, our forums are always open to you, and Support is only a chat away.
Thank you for choosing Qlik,
Qlik Support
Today, predictive analytics is being used to anticipate patient needs before they arise. Hospitals can now analyze historical patient data to forecast admissions, optimize staffing, and even predict potential complications. This proactive approach not only improves care but also reduces costs and increases efficiency.
Another major area of impact is personalized medicine. By analyzing genetic, lifestyle, and environmental data, healthcare professionals can create tailored treatment plans for individuals—leading to more effective interventions and better recovery rates.
As digital health records, wearable devices, and real-time monitoring become more common, the role of data in healthcare will only grow. Future professionals with strong data literacy skills will be at the forefront of this transformation.
To read more about how analytics is revolutionizing healthcare, check out: The Top 12 Transformative Insights in Healthcare | Qlik eBook
To learn how the Qlik Academic Program equips students and educators with free analytics software, hands-on training, certifications, and more, visit: qlik.com/academicprogram
Hi everyone,
Want to stay a step ahead of important Qlik support issues? Then sign up for our monthly webinar series where you can get first-hand insights from Qlik experts.
The Techspert Talks session from July looked at Data Pipelines and Transformations.
But wait, what is it exactly?
Techspert Talks is a free webinar held on a monthly basis, where you can hear directly from Qlik Techsperts on topics that are relevant to Customers and Partners today.
In this session covered:
Click on this link to see the presentation
This month we would like to introduce you to Lisa Phillips. Lisa is based out of Sydney, Australia and loves introducing students to the power of Qlik products.
1. How long have you been with Qlik?
I have been working at Qlik as a technical trainer since 2016, so 9 years now.
2. How did you become an instructor?
In past job roles I have moved from Network Operations to Training to Technical Selling to Management, but I decided to go back to training as it is the most satisfying role, and I found that with Qlik.
3. What do you love about teaching Qlik courses?
I love helping people realize the potential and power of Qlik, some have tried to learn using google before coming to training and may say “I had no idea you could do ¼ of the things you have showed us!”, so I feel that there is still an important role for training customers using Qlik.
4. What is your favorite course to teach?
My favorite course to teach is the Data Modeling for Qlik Sense course, but as with all our solutions, we have to keep up with the continuous changes and enhancements to platforms and software which means it never gets boring!
If you’re in the APAC region, be on the lookout for one of Lisa's exciting Live Instructor Webinars and register. We know you'll be back for more!
Happy Learning!
KPIオブジェクトはそのままでは四角四面な感じです。
すっきりはしているのですが、遊び心を加えて図のようなKPIはいかがでしょうか?実は意外と簡単に作ることができます。
まずパワーポイントで背景用の画像を作ります。この図では図形の円を使用しています。塗りつぶしは単色で色は白、透明度は72%、線も単色の白、幅は9.5pt、スタイルは太い線と細い線の多重にしています。
この図を「図形として保存」で名前をつけて保存します。
そしてQlikのシート編集画面で KPI を作ります。スタイル指定の基本設定で背景を単色透明にし、背景画像として先ほど保存した円をメディアライブラリにアプロードして選びます。サイズは「常に適合」にして、位置は真ん中にしました。
スタイル指定のチャートで、タイトルとメジャーのフォントの大きさも適宜調整します。
そして、ちょっと面倒なのですが、プロパティパネルのプレゼンテーションの色から、「条件付きの色」も「ライブラリーカラー」もオフにして、白を選びます。これで完成です。
同じ方法で下記のようなKPIも作成できます。ちょっと画面が華やぎますね。
Happy Dueling !
** 過去の記事 **
Viz for Deck: 数字の視覚化アイデア
Viz for Deck: ダッシュボードの色を切り替える
AI 主導の世界で優位に立つには、いかに迅速にデータを意思決定に変換できるかにかかっています。だからこそ、自社の BI および分析のニーズに適したソリューションの選択が重要になります。Gartner® 社は、「Gartner® アナリティクス / BI プラットフォームの Magic Quadrant」で、15 年連続で Qlik をリーダーの 1 社として評価しました。2025年のレポートをご確認ください。
「Gartner® アナリティクス / BI プラットフォームの Magic Quadrant」で、Qlik が 15 年連続でリーダーの 1 社に評価された理由とは?無料のレポートで、その理由と BI 市場の全容をご確認ください。
無料のレポートを見る
Not sure where to begin or what you need to know to take the exam? We’ve got you covered! We created this How do I take a Qlik Certification exam? video that explains the exam process as well as the Qlik AI Specialist Certification Exam Details path to help you on your way to becoming certified.
Certification exam details
Duration: 120 minutes
Number of questions: 50
Passing score: 73%
This fifty question certification exam covers topics such as:
Preparation
To prepare for this exam, you can take the Qlik AI Certification Exam Preparation course.
Badge
After passing this certification exam, you are awarded the Qlik AI Specialist Certification badge. To learn more about the criteria for earning this badge, visit our Credly badging page.
Ready to take the exam? Log into Qlik Learning and get started today!
Welcome back to the final installment of our series covering the sections of Qlik Cloud’s New UI. In previous entries we have covered Insights, Analytics, Data Integrations, and half of Administration. Today we will be finishing up with Administration and with it this series.
Getting right into the second section of Administration, we’ll find API Keys. API keys are unique identified used to authenticate and authorize applications or users when accessing an API. In this section, users can generate and revoke keys as well as view the various details surrounding each of the API Keys. Please keep in mind that only users with the ‘Developer’ role can generate these keys.
The next section is Content Security Policy, also known as CSP. In this section you can add new origins, specifying their Name, and directive. You can also view the details of these origins, along with their created date, and last update. If you would like, you can also delete these origins as well in this section.
The OAuth section contains the OAuth clients that are tied to your tenant. OAuth is a security protocol that allows third-party applications to access API resources by disclosing end-user credentials. This section allows you to view the various information tied to the clients, such as the IDs tied to them, the name, status and type. Here you can create and delete these clients as needed to maintain security and performance for your tenant.
The Web section handles the web integrations for your tenant. These integrations can be a number of things such as web apps or mashups that are hosted on different sites. Using this section, users can stay up to date on interactions between third-party domains and their tenant. As with the previous sections, this section not only allows you to manage and view your web integrations, but create and delete them as well.
The Webhooks section of the Administration panel is used to set up event-based notifications that allow your Qlik environment to communicate with external systems in real time. In this section, like the others, you can create and delete these Webhooks, as well as view the various information about them.
The settings section contains the different settings for your tenant. Here you can change the names of your tenant. You can change the region of your Talend Cloud. Feature controls are here, allowing you to enable or disable data alerts. You can set up usage metrics for your tenant. The settings section contains so many toggles and settings that it could have its own blog. Let me know if you’d like to see that in a future installment.
The Identity Provider section allows users to connect Qlik Cloud to external authentication systems and configure single sign-ons. Qlik Cloud is compatible with many Identity Provider types and Providers that can be configured and deleted in this section. This section allows providers the issuers and the states of these providers here to help manage security on your tenant.
A Data Gateway is used with Qlik Cloud to connect your tenant to data stored on-premises or behind a firewall without exposing that data source directly to the internet. This section allows you to manage these gateways. Here you can see the type of gateway (Direct Access or Data Movement). The ID of the gateway, the status of it, and the space that the gateway is in. If for some reason your data is not connecting, this section is a great first step to see if it is in a connected state.
The Learn section is ‘Your center for knowledge and growth’. Here you will find instructional articles and videos that can help you learn more about what is possible with Qlik Cloud. Here you’ll also find links to ask the community a question, get more training working with Qlik Cloud, and an option for support if needed.
In any subscription-based business model, one of the primary goals is to retain its customers. Also, with the increase in market competition, it is crucial to identify ‘unhappy’ customers at an early stage so as to provide additional benefits and retain them. Churn prediction refers to determining which consumers are most likely to abandon a service or terminate their membership. To be able to predict churn gives businesses the necessary edge since getting new customers is sometimes more expensive than keeping old ones.
Ref: https://www.opexengine.com/keep-customer-churn-rate-under-control-or-labor-like-sisyphus/
The application of Machine learning techniques to understand & predict customer churn isn’t something new. Several ML algorithms have been used in the field of telecom, banking, insurance, etc. to detect early churn signals. However, just relying on an ML algorithm’s output to understand whether a customer will churn or not isn’t really an optimal approach anymore. To have a thorough understanding of the churn analysis process, the need to amalgamate historical data(what happened in the past?) with the predicted outcome(what will happen in the future?) is paramount.
This is where Qlik Sense’s visual analytics platform serves as an effective solution. Now, using advanced analytics connectors within Qlik Sense SaaS, users can build a Machine Learning model in an AutoML platform, consume the predictions in Qlik Sense and use them along with the Qlik’s data model to take advantage of things such as:
If you want to understand the entire workflow to integrate 3rd-party ML endpoints within Qlik Sense, I highly recommend going through this first part that I wrote a few days back. The generic workflow is depicted below.
In this specific tutorial, we are going to analyze customer churn behavior for a telecom company by building an end-to-end Qlik Sense app and leveraging both historical as well as predicted data. For building the Machine Learning model and hosting the endpoint, we will use the Amazon SageMaker platform. We will keep our focus on building the Qlik Sense app and not on developing the ML model.
Pre-requisite: To be able to use Analytics Endpoints the "Enable machine learning endpoints" parameter should be enabled in the Management Console.
First, let us load the source data into Qlik Sense using the Data load editor.
We will analyze our dataset in detail when we build our ‘descriptive’ dashboard but for now we know that we have 15 attributes and 3333 records that describe the profile of each customer of the telecom operator.
The last attribute, Churn, is known as the target attribute–the attribute that we want our ML model to predict to know if a customer will churn or not.
Our next step is to build the churn prediction model. The target is to classify each customer into either of the two categories — churn or not churn. Therefore, this is a binary classification problem. We will be leveraging SageMaker Autopilot that allows us to automatically build, train, and tune the best machine learning model based on our data without having to write much code.
Credit: Amazon Web Services YouTube
If you are just getting started with SageMaker Autopilot, here is a great video from AWS to help you understand the basics. I use the describe_auto_ml_job API to look up the best algorithm selected by the SageMaker Autopilot job.
Finally, we will create our model based on the best candidate (automl-churn-28–18–16–29r2UGiyXI-011–5e61e1c5) & deploy it to a hosted endpoint. When the endpoint is ready, the endpoint status will change to ‘InService’ like below.
To make it easier for you to learn about how I trained & deployed my model in SageMaker, I will attach my Python notebook along with this blog.
Now that we have the model endpoint ready for inference, we will send all the fields required by the model from QS to predict if a customer would churn or not. Please note that we will only send 14 attributes and exclude the last one(churn) since we want that prediction to be made by the model.
To do so, we go to the Data load editor and create a new SageMaker connection like below. You can read more about creating a new connection here.
You should now see the SageMaker_Autopilot_churn name in your list of connections. Now, click on ‘select data’ to start sending your data from QS data model to SageMaker.
Click on ‘Insert script’ to get the script in the editor.
Please note how I have changed the raw script that we got from our connection to include all the 14 fields to be sent to our endpoint. Like our previous use case, we use RowNo( ) here as a field to associate the source data & the returned prediction table.
Here’s a peek at our data model after the data is loaded.
Let’s quickly check what is returned by the ML model based on the data we sent from Qlik Sense.
So, for every customer row, we have a predicted_label field that shows whether the customer will stay or leave. We also have the individual class probabilities for deeper analysis.
Our final step is to build a Qlik Sense app so we can perform our analysis and present it to the stakeholders.
We will segregate the app into 3 sheets as shown below each serving its purpose:
Goal: This sheet will help us understand the historical source data & allow for detailed analysis.
First, I want to understand the distribution of a couple of features and since we have 15 of them, I won’t visualize all of them but highlight the ones that my stakeholders are interested in. In terms of visualization, I will use a container object and add the distributions as histograms like below.
We can see that most of the fields (Day mins, Eve mins, etc.) have a normal distribution while Cust Serv Calls appear to be positively skewed.
I also wanted to highlight how the target attribute(Churn) was distributed since it is important to know the reality of how many customers can actually churn. Looks like 14.49 % of the customers did churn.
Next, since our data is high-dimensional (10+ features) and I want to enable detailed analysis of individual customers, choosing a visualization that works well with multidimensional data was crucial. I decided to go with a Parallel coordinate plot extension that I built sometime back.
Finally, putting everything together here’s our Descriptive dashboard.
Let’s do a simple analysis. I want to compare a customer who wants to churn with one that does not. So, I randomly select two such rows.
This view allows us to easily compare all the 11 numerical attributes. So, looks like both of these customers are new customers(observe acc_length=1). The orange line represents Churn=‘True’ and the cyan represents Churn=‘False’. For most of the features, we see the lines in a criss-cross form which helps us understand how these 2 customers differ. One thing that stands out is how the customer who churns makes 5 customer service calls in just a day and the other one makes 1. This gives us an indication that the orange customer might have faced some issues with the operator.
Goal: This sheet will help us understand the churn predictions that we made using SageMaker & our model’s performance.
Let’s see how our overall predictions looks like.
The predictions are almost similar to the ground truth.
Next, I want to visualize the churn predictions by each state so the telecom operator can keep their focus on those ‘risky’ states.
This is a great example of how using Qlik’s associative property, we were able to integrate both historical and predicted data.
It is also important to understand what mistakes the ML model makes. False negatives are the most problematic because the model incorrectly predicts that a churning customer will stay. The best way to evaluate our model would be to draw a confusion matrix like below.
We have 17 such cases. We can select this ‘17 block’ from our matrix and perform detailed analysis of the special cases by analyzing both descriptive & predictive sheets.
Predictive dashboard:
Our final piece is the ‘What-if’ scenario builder. Personally, I love this native capability of Qlik Sense as it allows us to look beyond traditional analysis. Also, note how easy & quick it is to build this. I have used a custom object called ‘variable input’ that allows me to include sliders, dropdown & text fields.
The ‘Will the customer churn?’ is a KPI object and uses a Server side extension function ScriptAggrStr()as a chart expression which allows us to get predictions in real-time by passing the values dynamically from the input boxes. Here’s the expression -
endpoints.ScriptAggrStr('{"RequestType":"endpoint", "endpoint":{"connectionname":"Amazon_SageMaker_Telco"}}',vState,vActLen,vIntPln,vVmailPln,vVmailMsg,vDayMins,vDayCalls,vEveMins,vEveCalls,vNightMins,vNightCalls,vIntMins,vIntCalls,vCustServCalls)Let us do quick & simple what-if analysis. From our Descriptive sheet, we noted that the field Cust Serv calls might be an important one. After all, a happy customer doesn’t need to call customer service. To really prove that correlation, let’s play around.
And looks like the hypothesis makes sense! However, please note that this is just one factor. I tried increasing the Int’l Mins to 15 instead of 12 and even though I had a lot of customer service calls, the prediction was False.
So, maybe providing more Int’l Mins to the customer would be a great idea to retain them. This kind of insight can help businesses dealing with churn to really understand the pitfalls and improvise on them even at a granular level.
That brings us to the end of this exciting blog. The tutorial is a detailed one as the whole idea was to allow Qlik users to quickly adapt to these capabilities and understand the process end-to-end. Let me know what you think!
~Dipankar, Qlik R&D
AI は未来の技術ではなく、既に今日のビジネスに欠かせない技術として幅広い分野で貢献しています。
本 Web セミナーでは、以下を実現する実践的なヒントやワークフロー、そして AI から価値を得るための知識を共有します。また、先進的な企業の具体的な導入事例や成功事例を通して、データを主要なビジネスワークフローや戦略目標を推進する AI 主導型アプリケーションへと変革する方法をご紹介します。
満席をいただいた今回のユーザーミートアップは、Qlik Luminary & 幹事の萬様が司会を務められました。同じく幹事の荻本様より、4月に開催された意見交換会などの活動報告がありました。なお、次回は「データガバナンス」をテーマとした意見交換会の開催が予定されています。ぜひお楽しみに!
最初は、アステラス製薬様より「データドリブンな意思決定に Qlik Sense を ~わたしたちの 3 年間の取組み~」と題して、 BI 専任チームより Qlik アクセスのためのハブ作成、マネジャーへの NPrinting 配信などの取り組みをご紹介いただきました。
続くヒューマンアカデミー様からは、同社の学習プラットフォームのカスタマージャーニーにおける解約防止のためのキーポイントとそこで見るべきデータととるべきアクションといったビジネスプロセスなどをご紹介いただきました。
NECPC 様からは新しいプロジェクトに対応するため、短期間で Qlik Answers の検証を終え、わずか数ヶ月の導入期間・運用で問い合わせの削減という着実な成果を収めた事例を、デモを交えてご紹介されました。
前回に引き続きご登壇いただいた万葉倶楽部・コグニア様は、Qlik Sense を活用した顧客・営業分析の事例として、来館されたお客様のデータに基づき必要な施策を取ることで再訪率を高める取り組みなどをお話しされました。
ユーザー登壇の最後は学研様からの Qilk Connect 参加報告でした。Qlik の最先端に触れることのできるまたとない、かつ楽しい機会であったことを多くの写真と共に熱く語られました。
最後は Qlik より Qilk Connect で発表された数多くの新製品をご紹介しました。また、 第5回データソンが翌日 19日から始まることと、次回のユーザーミートアップと Qlik AI Reality Tour Tokyo が 10月 28日に同日開催されることが発表されました。ぜひ今からこの日は1日空けておいてください!
福岡から駆けつけた幹事松田様の乾杯で始まった懇親会では、新たに参画されたアドボケイトメンバーの紹介などもあり、いつも以上にユーザー様同士の交流が深まっていたようです。中には「次回のミートアップではぜひ登壇したい」と Qilk 社員にお声がけされたユーザー様もいらっしゃいました(ご登壇希望のユーザー様は、営業担当または Marketingjp@qlik.com までご連絡ください。ぜひよろしくお願いします!)。
本日、ご参加・ご登壇いただいた皆様、ありがとうございました!
エージェンティック AI とオープンレイクハウスという新しいソリューションを備えた今後の Qlik にぜひご期待ください。次回お会いするのを楽しみにしております。
Transformational. Innovative. Powerful. These are just a few of the inspiring terms customers use to describe Qlik and our product suite. Customer feedback and input are critical to Qlik’s success, and we regularly hear directly from our most active users through Qlik Nation, our gamified customer engagement hub.
Through interactive challenges and activities, Qlik Nation members connect, learn, and engage with Qlik and with each other. By completing challenges in the platform, members can receive early notification of new product features, boost knowledge through quality educational content, and have opportunities to influence the product roadmap. Qlik Nation also allows customers to demonstrate skills, network with peers, and amplify their personal brand. All while having fun and being rewarded!
And now, Qlik Nation members will be able to complete challenges while visiting Qlik Community. Current members will see a new carousel on the Qlik Community homepage inviting them to complete challenges, making it even easier for you to engage and earn points.
Customers are at the heart of everything we do, and Qlik Nation offers an exclusive experience for our most dedicated and passionate fans (Qlik Nation is a complementary platform to Qlik Community, which has open membership). What do our members say about their experience in Qlik Nation?
If you’re a Qlik end-user and want to learn more about how to join Qlik Nation, please email QlikNation@qlik.com. We’d love to hear from you!
Wharton Business School recently published an article that made a simple but powerful point. When working with data, don’t start by asking what data you have. Start by asking what decision you’re trying to make. (Wharton, 2024 Better Decisions with Data: Asking the Right Question - Knowledge at Wharton)
Once you know what you’re trying to decide, you can figure out what kind of data is helpful. Otherwise, you may spend time analyzing numbers that don’t matter.
It’s also important to stay curious. Be willing to question what you think you know. Sometimes the real insight comes from looking at things in a new way or noticing what’s missing.
AI is powerful and fast, but it doesn’t understand your goals, context, or values. That’s why human thinking is essential; we need people to see the big picture, ask the right questions, and make ethical, responsible decisions.
The Qlik Academic Program offers free access to powerful analytics tools, training, and certifications. Students build career-ready skills, professors bring real-world tools into the classroom, researchers uncover insights faster, and universities boost innovation in data education.
It’s free and it’s about learning to think with data.
Learn more: qlik.com/academicprogram
Updated: Release Date added (26th June 2025) and note added regarding the error users will encounter if they update before the redirect URI is configured.
Updated: Android Release Date added (16th July 2025)
Hello Qlik admins,
This post is intended for customers who use the Qlik Sense Client-Managed mobile app with Microsoft Intune policy management practices as described in Azure app registration for Qlik Sense Client-Managed Mobile.
Qlik anticipates the release of the Qlik Sense Client-Managed Mobile app version 1.31.1 for iOS on June 26th. With this release comes an update to the integrated Microsoft Intune version to 20.5.0, which will also update the Microsoft authentication protocol in use.
Many devices will automatically update the mobile app build in the background. To prepare for the update and to continue utilizing Microsoft Intune/Entra policy management of the Qlik Sense Client-Managed Mobile app, pre-configure the new redirect URI msauth.com.qlik.qliksense.mobile://auth in your Azure portal.
If a client is updated and the redirect URI has not been configured, the end user will see the error Failed to authenticate using OAuth. See Qlik Sense Client Managed mobile app on iOS: Failed to authenticate using OAuth for details.
Qlik supports only the current mobile app version in the app store. The end user migration to the new app is at the discretion of the customer; however, it is recommended all users upgrade immediately.
It is possible for users to continue Intune governance control with old and new mobile app versions.
Note that removing the old redirect URI (qliksense-intune://com.qlik.qliksense.mobile) for the mobile app versions before 1.31.1 will result in the old app no longer retrieving a policy from the Intune/Entra tenant.
For instructions on how to set up the Qlik Sense Client-Managed Mobile client with Microsoft Azure and Intune, see Add an Azure app registration for Qlik Sense Client-Managed Mobile | help.qlik.com. These instructions will be updated on the initial release of Qlik Client Managed mobile version 1.31.1.
The Android version of the Client-Managed Mobile app has been updated on the 16th of July.
Thank you for choosing Qlik,
Qlik Support
今年で 5 回目となる Qlik データソンに参加してみませんか?
今回のテーマは「デザイン」だけ!個人でもチームでも、センスとアイデアを存分に発揮して、Qlik Sense で魅せるダッシュボードを作成してください。もちろん、初心者のご参加も大歓迎です!アワード受賞者には豪華賞品も!お申し込みは、7/11(金)17:00 まで受付中です。奮ってご参加ください!
【課題】
【対象者】
【開催概要】
申込締切:7/11(金)17:00
成果物締切:7/18(金)17:00
投票期間:7/23(水)- 8/1(金)17:00(参加者による Web 投票および Qlik 審査員による審査)
授賞式:8/7(木)17:00 - 19:30(東京の某会場とオンライン配信のハイブリッド式)