Understanding customer behavior is top of mind for every business today. Gaining insights into why and how customers buy can help grow revenue. But losing customers (also called customer churn) is always a risk, and insights into why customers leave can be just as important for maintaining revenues and profits. Machine learning (ML) can help with insights, but up until now you needed ML experts to build models to predict churn, the lack of which could delay insight-driven actions by businesses to retain customers.
In this post, we show you how business analysts can build a customer churn ML model with अमेज़ॅन सेजमेकर कैनवास, no code required. Canvas provides business analysts with a visual point-and-click interface that allows you to build models and generate accurate ML predictions on your own—without requiring any ML experience or having to write a single line of code.
समाधान का अवलोकन
For this post, we assume the role of a marketing analyst in the marketing department of a mobile phone operator. We have been tasked with identifying customers that are potentially at risk of churning. We have access to service usage and other customer behavior data, and want to know if this data can help explain why a customer would leave. If we can identify factors that explain churn, then we can take corrective actions to change predicted behavior, such as running targeted retention campaigns.
To do this, we use the data we have in a CSV file, which contains information about customer usage and churn. We use Canvas to perform the following steps:
- Import the churn dataset from अमेज़न सरल भंडारण सेवा (अमेज़न S3)।
- Train and build the churn model.
- मॉडल परिणामों का विश्लेषण करें।
- मॉडल के खिलाफ परीक्षण भविष्यवाणियां।
हमारे डेटासेट के लिए, हम एक का उपयोग करते हैं सिंथेटिक डेटासेट from a telecommunications mobile phone carrier. This sample dataset contains 5,000 records, where each record uses 21 attributes to describe the customer profile. The attributes are as follows:
- राज्य – The US state in which the customer resides, indicated by a two-letter abbreviation; for example, OH or NJ
- खाता लंबाई - यह खाता जितने दिनों तक सक्रिय रहा है
- एरिया कोड – The three-digit area code of the customer’s phone number
- फ़ोन – The remaining seven-digit phone number
- अंतरराष्ट्रीय योजना – Whether the customer has an international calling plan (yes/no)
- वीमेल योजना – Whether the customer has a voice mail feature (yes/no)
- वीमेल संदेश – प्रति माह वॉइस मेल संदेशों की औसत संख्या
- दिन मिनट – The total number of calling minutes used during the day
- दिन कॉल – The total number of calls placed during the day
- डे चार्ज – The billed cost of daytime calls
- Eve Mins, Eve Calls, ईव चार्ज – The billed cost for evening calls
- Night Mins, रात कॉल, रात का चार्ज – The billed cost for nighttime calls
- Intl Mins, Intl Calls, इंटल चार्ज - अंतर्राष्ट्रीय कॉल के लिए बिल की गई लागत
- CustServ कॉल - ग्राहक सेवा पर की गई कॉलों की संख्या
- मंथन? – Whether the customer left the service (true/false)
अंतिम गुण, Churn?
, is the attribute that we want the ML model to predict. The target attribute is binary, meaning our model predicts the output as one of two categories (True
or False
).
.. पूर्वापेक्षाएँ
एक के साथ एक क्लाउड व्यवस्थापक AWS खाता निम्नलिखित पूर्वापेक्षाओं को पूरा करने के लिए उपयुक्त अनुमतियों के साथ आवश्यक है:
- तैनात ए अमेज़न SageMaker निर्देशों के लिए, देखें अमेज़न सेजमेकर डोमेन पर ऑनबोर्ड.
- Deploy Canvas. For instructions, see अमेज़ॅन सेजमेकर कैनवास की स्थापना और प्रबंधन (आईटी प्रशासकों के लिए).
- कैनवास के लिए क्रॉस-ओरिजिनल रिसोर्स शेयरिंग (CORS) नीतियां कॉन्फ़िगर करें। निर्देशों के लिए देखें अपने उपयोगकर्ताओं को स्थानीय फ़ाइलें अपलोड करने की क्षमता दें.
एक ग्राहक मंथन मॉडल बनाएं
First, let’s download the मंथन डेटासेट and review the file to make sure all the data is there. Then complete the following steps:
- में साइन इन करें एडब्ल्यूएस प्रबंधन कंसोल, कैनवास तक पहुँचने के लिए उपयुक्त अनुमतियों वाले खाते का उपयोग करना।
- कैनवास कंसोल में लॉग इन करें।
This is where we can manage our datasets and create models.
- चुनें आयात.
- चुनें अपलोड और चयन करें
churn.csv
फ़ाइल. - चुनें आयात आंकड़ा कैनवास पर अपलोड करने के लिए।
The import process takes approximately 10 seconds (this can vary depending on dataset size). When it’s complete, we can see the dataset is in Ready
स्थिति।
- To preview the first 100 rows of the dataset, hover your mouse over the eye icon.
A preview of the dataset appears. Here we can verify that our data is correct.
After we confirm that the imported dataset is ready, we create our model.
- चुनें नए मॉडल.
- Select the churn.csv dataset and choose डेटासेट चुनें.
Now we configure the build model process.
- के लिए Target columns, चुनना
Churn?
स्तंभ.
के लिए मॉडल प्रकार, Canvas automatically recommends the model type, in this case 2 श्रेणी की भविष्यवाणी (what a data scientist would call binary classification). This is suitable for our use case because we have only two possible prediction values: True
or False
, so we go with the recommendation Canvas made.
We now validate some assumptions. We want to get a quick view into whether our target column can be predicted by the other columns. We can get a fast view into the model’s estimated accuracy and column impact (the estimated importance of each column in predicting the target column).
- Select all 21 columns and choose पूर्वावलोकन मॉडल.
This feature uses a subset of our dataset and only a single pass at modeling. For our use case, the preview model takes approximately 2 minutes to build.
जैसा कि निम्नलिखित स्क्रीनशॉट में दिखाया गया है Phone
और State
columns have much less impact on our prediction. We want to be careful when removing text input because it can contain important discrete, categorical features contributing to our prediction. Here, the phone number is just the equivalent of an account number—not of value in predicting other accounts’ likelihood of churn, and the customer’s state doesn’t impact our model much.
- We remove these columns because they have no major feature importance.
- After we remove the
Phone
औरState
columns, let’s run the preview again.
As shown in the following screenshot, the model accuracy increased by 0.1%. Our preview model has a 95.9% estimated accuracy, and the columns with the biggest impact are Night Calls
, Eve Mins
, तथा Night Charge
. This gives us an insight into what columns impact the performance of our model the most. Here we need to be careful when doing feature selection because if a single feature is extremely impactful on a model’s outcome, it’s a primary indicator of लक्ष्य रिसाव, and the feature won’t be available at the time of prediction. In this case, few columns showed very similar impact, so we continue to build our model.
Canvas offers two build options:
- मानक निर्माण – Builds the best model from an optimized process powered by ऑटो एम.एम.एल.; speed is exchanged for greatest accuracy
- त्वरित निर्माण – Builds a model in a fraction of the time compared to a standard build; potential accuracy is exchanged for speed.
- For this post, we choose the मानक निर्माण option because we want to have the very best model and we are willing to spend additional time waiting the result.
The build process can take 2–4 hours. During this time, Canvas tests hundreds of candidate pipelines, selecting the best model to present to us. In the following screenshot, we can see the expected build time and progress.
मॉडल के प्रदर्शन का मूल्यांकन करें
When the model building process is complete, the model predicted churn 97.9% of the time. This seems fine, but as analysts we want to dive deeper and see if we can trust the model to make decisions based on it. On the स्कोरिंग tab, we can review a visual plot of our predictions mapped to their outcomes. This allows us a deeper insight into our model.
Canvas separates the dataset into training and test sets. The training dataset is the data Canvas uses to build the model. The test set is used to see if the model performs well with new data. The Sankey diagram in the following screenshot shows how the model performed on the test set. To learn more, refer to Amazon SageMaker कैनवास में अपने मॉडल के प्रदर्शन का मूल्यांकन.
To get more detailed insights beyond what is displayed in the Sankey diagram, business analysts can use a असमंजस का जाल analysis for their business solutions. For example, we want to better understand the likelihood of the model making false predictions. We can see this in the Sankey diagram, but want more insights, so we choose उन्नत मेट्रिक्स. We’re presented with a confusion matrix, which displays the performance of a model in a visual format with the following values, specific to the positive class—we’re measuring based on whether they will in fact churn, so our positive class is True
इस उदाहरण में:
- ट्रू पॉजिटिव (टीपी) - की संख्या
True
results that were correctly predicted asTrue
- True Negative (TN) - की संख्या
False
results that were correctly predicted asFalse
- झूठी सकारात्मक (एफपी) - की संख्या
False
results that were wrongly predicted asTrue
- झूठी नकारात्मक (एफएन) - की संख्या
True
results that were wrongly predicted asFalse
We can use this matrix chart to determine not only how accurate our model is, but when it is wrong, how often that might be and how it’s wrong.
The advanced metrics look good. We can trust the model result. We see very low false positives and false negatives. These are if the model thinks a customer in the dataset will churn and they actually don’t (false positive), or if the model thinks the customer will churn and they actually do (false negative). High numbers for either might make us think more on if we can use the model to make decisions.
चलो वापस चलते हैं अवलोकन
tab, to review the impact of each column. This information can help the marketing team gain insights that lead to taking actions to reduce customer churn. For example, we can see that both low and high CustServ Calls
increase the likelihood of churn. The marketing team can take actions to prevent customer churn based on these learnings. Examples include creating a detailed FAQ on websites to reduce customer service calls, and running education campaigns with customers on the FAQ that can keep engagement up.
Our model looks pretty accurate. We can directly perform an interactive prediction on the भविष्यवाणी करना tab, either in batch or single (real-time) prediction. In this example, we made a few changes to certain column values and performed a real-time prediction. Canvas shows us the prediction result along with the confidence level.
Let’s say we have an existing customer who has the following usage: Night Mins
40 है और Eve Mins
is 40. We can run a prediction, and our model returns a confidence score of 93.2% that this customer will churn (True
). We might now choose to provide promotional discounts to retain this customer.
Let’s say we have an existing customer who has the following the usage: Night Mins
40 है और Eve Mins
is 40. We can run a prediction, and our model returns a confidence score of 93.2% that this customer will churn (True
). We might now choose to provide promotion discounts to retain this customer.
Running one prediction is great for individual what-if analysis, but we also need to run predictions on many records at once. Canvas is able to run batch predictions, which allows you to run predictions at scale.
निष्कर्ष
In this post, we showed how a business analyst can create a customer churn model with SageMaker Canvas using sample data. Canvas allows your business analysts to create accurate ML models and generate predictions using a no-code, visual, point-and-click interface. A marketing analysist can now use this information to run targeted retention campaigns and test new campaign strategies faster, leading to a reduction in customer churn.
Analysts can take this to the next level by sharing their models with data scientist colleagues. The data scientists can view the Canvas model in अमेज़ॅन सैजमेकर स्टूडियो, where they can explore the choices Canvas AutoML made, validate model results, and even productionalize the model with a few clicks. This can accelerate ML-based value creation and help scale improved outcomes faster.
कैनवास का उपयोग करने के बारे में अधिक जानने के लिए देखें बिल्ड, शेयर, डिप्लॉय: कैसे व्यापार विश्लेषक और डेटा वैज्ञानिक बिना कोड एमएल और अमेज़ॅन सेजमेकर कैनवास का उपयोग करके तेजी से समय-समय पर बाजार प्राप्त करते हैं. बिना कोड समाधान वाले एमएल मॉडल बनाने के बारे में अधिक जानकारी के लिए देखें अमेज़ॅन सेजमेकर कैनवास की घोषणा - व्यापार विश्लेषकों के लिए एक दृश्य, बिना कोड मशीन सीखने की क्षमता.
लेखक के बारे में
Henry Robalino is a Solutions Architect at AWS, based out of NJ. He is passionate about cloud and machine learning, and the role they can play in society. He achieves this by working with customers to help them achieve their business goals using the AWS Cloud. Outside of work, you can find Henry traveling or exploring the outdoors with his fur daughter Arly.
Chaoran Wang is a Solution Architect at AWS, based in Dallas, TX. He has been working at AWS since graduating from the University of Texas at Dallas in 2016 with a master’s in Computer Science. Chaoran helps customers build scalable, secure, and cost-effective applications and find solutions to solve their business challenges on the AWS Cloud. Outside work, Chaoran loves spending time with his family and two dogs, Biubiu and Coco.
- कॉइनस्मार्ट। यूरोप का सर्वश्रेष्ठ बिटकॉइन और क्रिप्टो एक्सचेंज।
- प्लेटोब्लॉकचैन। Web3 मेटावर्स इंटेलिजेंस। ज्ञान प्रवर्धित। नि: शुल्क प्रवेश।
- क्रिप्टोहॉक। Altcoin रडार। मुफ्त परीक्षण।
- Source: https://aws.amazon.com/blogs/machine-learning/predicting-customer-churn-with-no-code-machine-learning-using-amazon-sagemaker-canvas/
- "
- 000
- 10
- 100
- 11
- 2016
- 7
- 9
- About
- में तेजी लाने के
- पहुँच
- लेखा
- सही
- कार्रवाई
- अतिरिक्त
- व्यवस्थापक
- प्रशासकों
- उन्नत
- सब
- वीरांगना
- विश्लेषण
- विश्लेषक
- अनुप्रयोगों
- उपयुक्त
- लगभग
- क्षेत्र
- विशेषताओं
- उपलब्ध
- औसत
- एडब्ल्यूएस
- BEST
- परे
- सबसे बड़ा
- सीमा
- निर्माण
- इमारत
- बनाता है
- व्यापार
- व्यवसायों
- खरीदने के लिए
- कॉल
- अभियान
- अभियान
- पा सकते हैं
- उम्मीदवार
- कैनवास
- वर्ग
- कुछ
- चुनौतियों
- परिवर्तन
- प्रभार
- विकल्प
- चुनें
- कक्षा
- वर्गीकरण
- बादल
- कोड
- सहयोगियों
- स्तंभ
- तुलना
- कंप्यूटर
- कम्प्यूटर साइंस
- आत्मविश्वास
- भ्रम
- कंसोल
- शामिल हैं
- जारी रखने के
- प्रभावी लागत
- सका
- बनाना
- बनाना
- निर्माण
- ग्राहक
- ग्राहक सेवा
- ग्राहक
- डलास
- तिथि
- आँकड़े वाला वैज्ञानिक
- और गहरा
- देरी
- निर्भर करता है
- तैनात
- विस्तृत
- निर्धारित करना
- सीधे
- प्रदर्शित करता है
- नहीं करता है
- शिक्षा
- सगाई
- अभियांत्रिकी
- अनुमानित
- उदाहरण
- मौजूदा
- अपेक्षित
- अनुभव
- विशेषज्ञों
- का पता लगाने
- आंख
- कारकों
- परिवार
- सामान्य प्रश्न
- फास्ट
- और तेज
- Feature
- विशेषताएं
- अंत
- प्रथम
- निम्नलिखित
- प्रारूप
- उत्पन्न
- लक्ष्यों
- अच्छा
- महान
- अधिकतम
- आगे बढ़ें
- होने
- मदद
- मदद करता है
- यहाँ उत्पन्न करें
- हाई
- कैसे
- HTTPS
- सैकड़ों
- नायक
- पहचान करना
- पहचान
- प्रभाव
- प्रभावपूर्ण
- महत्व
- महत्वपूर्ण
- उन्नत
- शामिल
- बढ़ना
- वृद्धि हुई
- व्यक्ति
- करें-
- निवेश
- अंतर्दृष्टि
- इंटरैक्टिव
- इंटरफेस
- अंतरराष्ट्रीय स्तर पर
- IT
- नेतृत्व
- प्रमुख
- जानें
- सीख रहा हूँ
- छोड़ना
- स्तर
- लाइन
- स्थानीय
- मशीन
- यंत्र अधिगम
- बनाया गया
- प्रमुख
- निर्माण
- प्रबंधन
- प्रबंध
- प्रबंध
- विपणन (मार्केटिंग)
- मास्टर की
- मैट्रिक्स
- अर्थ
- मेट्रिक्स
- मन
- ML
- मोबाइल
- मोबाइल फ़ोन
- आदर्श
- मॉडल
- अधिक
- अधिकांश
- नकारात्मक
- संख्या
- संख्या
- ऑफर
- अनुकूलित
- विकल्प
- ऑप्शंस
- अन्य
- सड़क पर
- आवेशपूर्ण
- प्रदर्शन
- प्ले
- नीतियाँ
- सकारात्मक
- संभव
- संभावित
- भविष्यवाणी करना
- भविष्यवाणी
- भविष्यवाणियों
- वर्तमान
- सुंदर
- पूर्वावलोकन
- प्राथमिक
- प्रक्रिया
- प्रोफाइल
- मुनाफा
- पदोन्नति
- प्रचार
- प्रदान करना
- प्रदान करता है
- त्वरित
- वास्तविक समय
- की सिफारिश की
- रिकॉर्ड
- अभिलेख
- को कम करने
- शेष
- हटाने
- अपेक्षित
- संसाधन
- परिणाम
- रिटर्न
- राजस्व
- की समीक्षा
- जोखिम
- रन
- दौड़ना
- स्केलेबल
- स्केल
- विज्ञान
- वैज्ञानिक
- वैज्ञानिकों
- सेकंड
- सुरक्षित
- सेवा
- सेट
- Share
- बांटने
- समान
- सरल
- आकार
- So
- समाज
- ठोस
- समाधान
- समाधान ढूंढे
- हल
- कुछ
- गति
- बिताना
- खर्च
- मानक
- राज्य
- स्थिति
- भंडारण
- रणनीतियों
- ले जा
- लक्ष्य
- टीम
- दूरसंचार
- परीक्षण
- परीक्षण
- टेक्सास
- पहर
- आज
- ऊपर का
- प्रशिक्षण
- यात्रा का
- ट्रस्ट
- TX
- समझना
- विश्वविद्यालय
- us
- उपयोग
- उपयोगकर्ताओं
- मूल्य
- सत्यापित
- देखें
- आवाज़
- वेबसाइटों
- क्या
- एचएमबी क्या है?
- या
- कौन
- विकिपीडिया
- काम
- काम कर रहे
- होगा