Welcome to Pet Clinic Center!

[email protected]
Appointment

Category Archives: Other Einstein features

  1. Home / 
  2. Archive by category "Other Einstein features"
Jul 12, 2024
Tableau and Salesforce: a powerful combination– Troubleshooting, Tricks, and Best Practices

In the previous chapters, we delved into the incredible power the combination of Salesforce and Tableau offers to organizations. By pulling together these world-class solutions, businesses can not only access a wide array of features but also unlock unique synergies that boost their operational efficiency and decision-making prowess.

Let us take a moment to reflect on the insights we have gathered so far.

Tableau’s advanced visualization tools make the wealth of data stored in Salesforce readily understandable and actionable. By crafting intuitive dashboards, teams across your organization can leverage Salesforce’s rich customer data to gain insights previously hidden in the complexity of raw data. Merging Salesforce data with information from other business sources also allows for a more holistic view of your business and its customers, enabling you to make decisions with confidence and precision.

We also discussed how bringing Tableau dashboards into the Salesforce CRM environment enhances user efficiency. Having visualized data within the same workspace where business activities take place saves precious time and prevents potential information loss that can occur during context switching. The power of Tableau’s Dashboard Starters and the seamless integration within Salesforce CRM workflows translate into convenience and deeper understanding, equipping your teams with the tools to make smarter, more informed decisions.

We delved into the fascinating world of Einstein AI and how its advanced insights can propel your Tableau dashboards to another level. Einstein AI’s easy-to-set-up models connect your analytics to actionable next steps. Coupled with Data Cloud for Tableau, this enables your organization to tap into unified data sources, providing a wide field of view of your customer’s journey.

And finally, we explored the full integration of Tableau CRM (previously referred to as CRM Analytics) within the Salesforce platform. This native solution amalgamates Salesforce’s comprehensive sales, service, and marketing data with Tableau’s visualization prowess, allowing businesses to detect trends, anticipate outcomes, identify anomalies, and enhance customer experiences.

In short, the marriage of Salesforce and Tableau is more than just the sum of its parts. It is a potent blend that unlocks the full potential of customer data, empowers users to work more efficiently, and uncovers advanced insights. By leveraging this powerful combination, organizations can make data-driven decisions with greater ease and accuracy, thereby boosting their overall performance. And this is the power of harnessing two world-class solutions to enhance your business’s strategic decision-making capabilities.

More Details
Jun 13, 2024
Introduction– Troubleshooting, Tricks, and Best Practices

This chapter will summarize why Tableau and Salesforce are such a powerful combination, with an emphasis on their capabilities for data analysis, visualization, and decision-making. Additionally, the chapter will provide tips on how to get started using Tableau and Salesforce in practice, with guidance on best practices and useful resources. It will also contain guidance on troubleshooting common issues. The chapter will also explain how to continue the learning journey, including recommended further reading. Lastly, the chapter will help you start using the knowledge gained to improve your data analysis and decision making skills.

Structure

The chapter covers the following topics:

  • Tableau and Salesforce: a powerful combination
  • Trouble shooting guidance
  • Troubleshooting guidance
  • Continuing the learning journey

Objectives

This chapter is designed to provide learners with a thorough understanding of the combined use of Tableau and Salesforce for data analysis and visualization, highlighting their unique strengths and synergies. It delves into the reasons why integrating Tableau with Salesforce can significantly enhance business decision-making capabilities.

Learners will also be equipped with essential tips and best practices for effectively starting with Tableau and Salesforce in practical, real-world scenarios. Furthermore, the chapter includes strategies for troubleshooting common issues that may arise in the Tableau and Salesforce environments.

It also guides learners to discover a range of useful resources, tools, and platforms that can support their journey in mastering these technologies. The importance of continuous learning is emphasized, with strategies provided for staying current with the latest trends and developments in Tableau and Salesforce.

Additionally, learners will find recommendations for further reading that can deepen their understanding and proficiency in using these tools. Finally, the chapter aims to encourage and empower learners to confidently apply the knowledge and skills acquired from this book in their data analysis and decision-making tasks.

More Details
Mar 16, 2024
Other Einstein features– Exploring Einstein AI and Advanced Analytics

There are many other features that are part of the Salesforce Einstein offering that could fall under the rubric of advanced analytics. Here we will consider the following:

  • Einstein lead scoring: This advanced analytics product utilizes machine learning techniques to assign a lead score to each lead based on their likelihood of converting. The score ranges from 1-99 and helps prioritize the leads for sales teams. It also provides insights into the factors that contribute to a lead’s score. By analyzing historical data and identifying patterns, Einstein Lead Scoring makes data-driven predictions, enabling sales teams to focus on the most promising leads.
  • Einstein opportunity scoring: Like Einstein lead scoring, this advanced analytics product uses machine learning techniques to score opportunities based on their likelihood of becoming Closed Won. The scoring system ranges from 1-99, and the scores are available as a field on the opportunity record, in list views, reports, and on the forecast page. By identifying conversion patterns, Einstein Opportunity Scoring helps sales teams concentrate on high-priority opportunities while making data-backed predictions.
  • Einstein opportunity insights: This advanced analytics product draws on machine learning and data analysis techniques to provide predictions about which deals are likely to be won, reminders to follow up, and key moments in a deal process. By examining historical data and patterns, Einstein Opportunity Insights helps sales teams make informed decisions and prioritize their efforts.
  • Pipeline inspection (Einstein deal insights + Tiered Einstein opportunity scores): Pipeline inspection assists sales managers in monitoring their team’s forecast for a given time period by providing a consolidated view of pipeline metrics, opportunities, week-to-week changes, AI-driven insights, close date predictions, and activity information. With Einstein Deal Insights, the product predicts the likelihood of winning deals within the current month and provides additional insights from Einstein Opportunity Scoring and Cases. The tiered Einstein Opportunity Scores categorize scores into High, Medium, and Low tiers, making it easier for sales managers to track the progress and prioritize efforts effectively.
  • Einstein forecasting: Leveraging artificial intelligence technology, Einstein Forecasting brings more certainty and visibility to sales forecasts. It helps improve forecasting accuracy, provides forecast predictions, and offers suggestions for taking a better approach if projected performance is suboptimal. By examining historical data and trends, Einstein Forecasting can support sales teams with more accurate and data-driven forecasts.
  • Einstein account insights: This product uses advanced analytics techniques, such as sentiment analysis and text mining, to provide valuable information about accounts. account insights can help sales teams stay on top of news affecting their businesses, including account expansion or cost-cutting, changes in company leadership, and involvement in merger and acquisition talks. By identifying these insights, Einstein account insights helps teams make more informed decisions and take advantage of new opportunities.
  • Einstein automated contacts: This advanced analytics product uses email and event activity to find new contacts and opportunity contact roles to add to Salesforce, making the process more efficient for sales teams and admins. The product can either suggest new contacts to be added by sales team members or automatically associate opportunity contact roles in the background. By utilizing machine learning techniques, Einstein’s automated contacts streamline the process of managing contacts and opportunities in Salesforce.
  • Recommended connections: Although the word Einstein is not used in the product name, recommended connections is an AI-driven feature that provides suggestions for connecting with leads and contacts based on existing relationships within the company. The product showcases colleagues with the strongest connections to an individual, helping facilitate conversations with prospects. This intelligent feature can help sales teams make more meaningful connections by tapping into their colleagues’ networks and leveraging existing relationships.
More Details
Jan 30, 2024
Deeper dive in Einstein discovery – Exploring Einstein AI and Advanced Analytics

Salesforce: Advanced analytics capabilities

The following sections will dive into the advanced analytics capabilities within Salesforce and CRMA. This will teach you the options for working with advanced analytics within Salesforce prior to diving into the hands-on case.

Deeper dive in Einstein discovery

Einstein Discovery is a powerful tool within the context of advanced analytics. It can seamlessly incorporate Artificial Intelligence (AI) and machine learning into a business user’s workflow, allowing for the creation of predictive models without the need for data scientists or advanced developers. To truly leverage this platform’s potential, users must understand their data, interpret model outcomes, and correctly configure training datasets.

Advanced analytics involves sophisticated techniques and tools that delve beyond the traditional realm of BI to uncover deeper insights, make predictions, and offer recommendations. Einstein Discovery aligns with several aspects of advanced analytics, such as machine learning, pattern matching, and forecasting. Utilizing a no-code AI approach, the platform embeds algorithms to train its models, eliminating the need for manual coding.

Choosing the right features and incorporating business knowledge is an important process in utilizing Einstein Discovery effectively. Business representatives and data analysts need to collaborate from the start of the model development process. This collaboration ensures that the most relevant predictors are chosen and that the model’s outputs are aligned with business needs and goals.

Some key practices for model enhancement in Einstein Discovery include segmenting datasets into different models, handling multicollinearity, managing diverse inputs, detecting and handling outliers, and choosing the optimal bucketing method for every use case. It is essential to balance the accuracy that the model delivers with the need for understanding why the prediction was made, with business requirements often guiding these decisions.

Segmentation can improve prediction quality by creating separate models for different data segments, accommodating the behavior of each segment in the model. Tests such as examining distributions of input variables can be used to determine when segmentation is a viable strategy.

Multicollinearity occurs when dependent variables can be linearly predicted from each other, causing potential issues in model quality. Methods to address multicollinearity include a thorough investigation of data, understanding business relations between variables, and using Einstein Discovery to highlight problematic relationships.

Outliers can impact the accuracy and explainability of models. Detecting and managing outliers can improve model quality by reducing noise. Einstein Discovery can recommend an approach for handling outliers, but business input is crucial in the decision-making process.

Bucketing is an essential consideration in model quality and explainability. The right balance between optimal model metrics and clear explanations can be achieved by using different bucketing methods such as bucket by count, manual bucketing, bucket by width, or Einstein Discovery’s recommended buckets.

Lastly, adding explicit second-order variables representing interactions between different features can also improve model accuracy. However, this method should be used with caution, taking into account potential limitations such as the number of possible column value combinations and the variety of data reflecting those combinations.

Einstein Discovery provides a powerful means of advanced analytics by incorporating machine learning, pattern matching, and forecasting techniques seamlessly into the business user’s workflow. Close collaboration between business users and data analysts ensures that the right features are chosen and that the model is both accurate and relevant to the company’s goals. Adopting various model enhancement practices, such as strategically segmenting datasets and fine-tuning bucketing methods, can help perfect the insights provided by Einstein Discovery and maximize its value as an advanced analytics solution.

More Details
Oct 7, 2023
Advanced analytics – Exploring Einstein AI and Advanced Analytics

Advanced Analytics involves the independent or partially independent analysis of data or content using complex methods and tools. These often surpass the capabilities of standard Business Intelligence (BI), allowing for the uncovering of more profound insights, the making of predictions, or the provision of suggestions. Techniques employed in advanced analytics encompass data or text mining, machine learning, pattern identification, forecasting, visual representation, semantic and sentiment analysis, network and cluster analysis, multivariate statistics, graph analysis, simulation, complex event processing, and neural networks.

Advanced analytics applications in businesses are broad and varied, covering areas such as customer acquisition and retention, marketing efforts enhancement, risk management, and product development and innovation.

With the aid of advanced analytics, businesses can identify customer preferences, target their marketing efforts, foresee potential risks, and innovate in product development. Let us delve deeper into these applications:

  • Customer acquisition and retention: Advanced analytics can process customer interaction data, market research, and feedback to identify customer preference trends. Salesforce’s intelligent Customer 360 platform can be used here to provide a unified customer view, allowing businesses to meet and exceed customer expectations effectively.
  • Enhancing marketing efforts: Machine learning, business intelligence, and predictive modeling can enable companies to develop sophisticated marketing campaigns. Salesforce Marketing Cloud can assist in delivering personalized experiences to customers, tracking real-time behavior changes, and making data-driven decisions.
  • Improving risk management: Advanced analytics tools can model scenarios and forecast risks, guiding enterprises toward strategic risk management plans. Salesforce Shield provides a set of integrated services for managing business risks, from archiving sensitive data to implementing fine-grained user permissions.
  • Product development and innovation: By analyzing customer needs, advanced analytics tools can identify areas of improvement and potential new product niches. Salesforce’s Product Development Cloud can manage the entire lifecycle of product development, from ideation to launch.

Real-world applications of advanced analytics

Various global brands have harnessed the power of advanced analytics to drive their success. For instance, Amazon uses advanced analytics to provide personalized customer experiences. Starbucks optimizes its menu and product offerings through data analytics. American Express uses predictive modeling to anticipate potential customer churn and optimize marketing efforts.

Tableau, with its powerful data visualization capabilities, can be used to replicate these successes by presenting complex data in an understandable and actionable format. Whether it is predicting customer behavior like Amazon, optimizing product offerings like Starbucks, or forecasting customer churn like American Express, Tableau is a versatile tool in the hands of data scientists and analysts.

Advanced analytics is crucial for fostering innovation and improving business operations. By utilizing predictive analytics, businesses can make better-informed decisions and model outcomes beforehand. This capability allows businesses to craft strategic plans for all areas of operations, from customer service to digital marketing.

With technology’s evolution, the potential applications and capabilities of data science tools, like Salesforce and Tableau, are continually expanding. This advancement has reflected in the growing number of organizations planning to integrate advanced analytics into their decision-making models.

The future of advanced analytics will likely see more complex algorithms, more data science, and more process automation. Both Salesforce and Tableau, with their robust and continually improving features, are well-positioned to support this evolution.

More Details
Sep 1, 2023
Objectives – Exploring Einstein AI and Advanced Analytics

Introduction

This chapter will focus on the concept of advanced analytics and its applications in Tableau and Salesforce. The chapter will begin by defining advanced analytics and its capabilities in providing deeper insights and predictions from data. The chapter will then cover the use of advanced analytics in Tableau, highlighting relevant features. Additionally, the chapter will delve into advanced analytics in Salesforce, including its Einstein platform and its capabilities for machine learning and AI-powered insights. Lastly, the chapter will guide how to create a combined analytical use case across Tableau and Salesforce, leveraging the strengths of both platforms for enhanced data analysis and decision-making.

Structure

The chapter covers the following topics:

  • Advanced analytics
  • Using advanced analytics in Tableau
  • Using advanced analytics in Salesforce
  • Combining Tableau and Salesforce for advanced Analytics

Objectives

This chapter provides learners with a comprehensive understanding of advanced analytics and its significant role in interpreting data and aiding decision-making. It explores the potential of advanced analytics to yield deeper insights and more accurate predictions. Learners will discover how to harness the capabilities of advanced analytics in Tableau, leading to robust data visualization and exploration. The chapter also imparts knowledge about Salesforce’s Einstein platform, which incorporates machine learning and artificial intelligence to facilitate advanced analytics. Additionally, it explains how Salesforce utilizes advanced analytics to enhance customer relationship management and other business functions.

A key focus of the chapter is teaching learners how to create a combined analytical use case that leverages the strengths of both Tableau and Salesforce for improved data analysis. This involves understanding the integration and synergies between these platforms, which is crucial for optimizing their use in a business context. Finally, learners are encouraged to apply the techniques and knowledge acquired to real-world problems. This application not only enhances their data analysis skills but also bolsters their strategic decision-making capabilities, equipping them with the tools to make informed, data-driven decisions in various business scenarios.

More Details
Mar 13, 2023
Making a dashboard – Blending Tableau with Traditional CRM Analytics

A dashboard is an engaging compilation of widgets that display the results of data queries. In this section, you will create a dashboard with an interactive chart and a list widget. You will incorporate the lens from the previous step and explore tools in the dashboard designer.
To incorporate a lens into a dashboard, you need to clip it. Clipping the lens allows CRM Analytics to add the query as a step in a new dashboard (or the most recently used open dashboard).

  1. In your newly created lens, click the Clip to Designer icon, marked in the following screenshot, to clip the query.

Figure 8.20: Clip to designer icon

  1. Under Display Label, enter Breakdown by Industry and click Clip to Designer.
  2. CRM Analytics will open the dashboard designer and add the query in the query panel. Breakdown by Industry will be displayed under the opportunity_history dataset.

Figure 8.21: Lens added to designer with query name showing

  1. Drag the Breakdown by Industry query onto the new dashboard grid.
  2. Resize the chart by dragging its corner to make it larger. The result should look like the following screenshot:

Figure 8.22: Query chart resized on dashboard
Widgets are the basic building blocks of a dashboard, providing various functions such as displaying key performance indicators, filtering dashboard results, visualizing data using interactive charts, or showing record-level details in tables. In this step, you will add a list widget to enable dashboard users to facet all the charts in the dashboard.

  1. Drag the List widget icon, shown in the screenshot, from the left side onto an empty space on the dashboard underneath the chart.

Figure 8.23: List widget being added to dashboard

  1. Click on the List widget and select Industry.
  2. Click Create in the window shown in the next screenshot:

Figure 8.24: Industry field selected for list

  1. Select the list widget by clicking on it.
  2. In the Properties panel on the right, click the Query tab.
  3. Ensure that both Apply global filters and Broadcast selections as facets are selected.
  4. Under Selection Type, choose Multiple Selection, shown in Figure 8.25:

Figure 8.25: List widget properties

  1. Save your dashboard by clicking the Save button.
  2. Enter My Test Dashboard as the title of your new dashboard, and select App | My Test App from the dropdown menu, as shown below:

Figure 8.26: Save dashboard dialogue

  1. Click Save to complete the process. You can preview your dashboard, which should look like this:

Figure 8.27: Completed test dashboard
You have now created a basic dashboard. We hope you will explore the potential of CRM Analytics much further on your own, but for now we will move on to Einstein Discovery, the machine learning engine that powers CRM Analytics.

More Details
Dec 4, 2022
Importing a dataset – Blending Tableau with Traditional CRM Analytics

Importing a dataset

CRM Analytics can work with many different kinds of data, both internal to the Salesforce platform and external, such as in a Snowflake data warehouse. To keep things simple, we will simply get our data from a CSV file. Start by downloading the file: https://developer.salesforce.com/files/opportunity_history.csv. This file is used for several Salesforce tutorials, and we will make use of it as well, for instance: https://trailhead.salesforce.com/content/learn/modules/einstein-discovery-basics/build-your-crm-analytics-dataset.

Our next step is, therefore to import the data from the CSV file into a CRM Analytics dataset, which can be done using the following steps:

  1. On the Analytics Studio home tab, click Create, select Dataset, and then choose CSV File, as shown in Figure 8.5:

Figure 8.5: Dataset creation menu showing CSV file option

  1. In the file-selection window that opens, locate the CSV file you downloaded, opportunity_history.csv, select it and then click Next. You can see this in the following screenshot:

Figure 8.6: File selection dialogue

  1. In the Dataset Name field, you can change the default name (opportunity_history), as shown below. By default, Analytics Studio uses the file name as the dataset name, which cannot exceed 80 characters as shown in the following figure:

Figure 8.7: Dataset name field

  1. Choose the app where you want to create the dataset. By default, Analytics Studio selects My Test App.
  2. Click Next. The Edit Field Attributes screen appears, shown in Figure 8.8, where you can preview the data and view or edit the attributes for each field.

Figure 8.8: Edit field attributes screen

  1. For now, accept the defaults and click Upload File. Analytics Studio uploads the data, prepares, and creates the dataset while showing progress as it occurs. You can see this in the following screenshot:

Figure 8.9: File upload progress
Once finished, you will see details about the dataset you created. If you do not see the dataset details, check your Datasets or search for opportunity_history in Analytics Studio.

More Details
Mar 14, 2022
Objectives – Blending Tableau with Traditional CRM Analytics

Introduction

This chapter will introduce CRM Analytics and its importance in understanding and improving customer relationships. It will begin by providing an overview of CRM analytics and its key features, including creating datasets and lenses to analyze customer data. Additionally, the chapter will explain how to create an Einstein Discovery model within Salesforce and use it from within the CRM Analytics platform. Lastly, the chapter will detail the use of the CRM Analytics Tableau Output Connector, which allows for the seamless integration of Salesforce data into Tableau for further analysis. Overall, this chapter will provide a comprehensive understanding of the capabilities and benefits of CRM Analytics within Salesforce and its integration with Tableau.

Structure

The chapter covers the following topics:

  • Introducing CRM Analytics
  • Creating Datasets, Lenses, and Dashboards in CRM Analytics
  • Building a lens
  • Creating an Einstein Discovery Model and using it from CRM Analytics
  • Using the Tableau Online Output Connection

Objectives

In this chapter, learners will develop a thorough understanding of CRM Analytics and its crucial role in managing and enhancing customer relationships. They will delve into the key features of CRM analytics, including how to create datasets and lenses for effective customer data analysis.

The chapter guides learners through creating an Einstein Discovery model within Salesforce and demonstrates how to utilize it within the CRM Analytics platform. A significant focus is placed on employing the CRM Analytics Tableau Output Connector, which facilitates the seamless integration of Salesforce data into Tableau. This includes learning how to export Salesforce data for use in Tableau and maximizing the capabilities of the CRM Analytics Tableau Output Connector.

Learners will gain a comprehensive understanding of the functionalities and benefits of CRM Analytics within Salesforce, particularly in its integration with Tableau. By the end of the chapter, they will be equipped to apply their knowledge of CRM Analytics and Tableau in a way that significantly improves the quality of customer relationships and enhances business decision-making.

More Details
Dec 30, 2021
Setting up SSO between Salesforce and Tableau Online – Integration, Authentication, and Tableau Viz LWC

When you embed dashboards from Tableau Online in Salesforce, you will normally have to log in with your Tableau credentials to see the dashboard, which can be quite annoying to users in the long run. To avoid this, you have the option of setting up SSO between the two environments.
This is a complex process, but worth the effort. To set up a SSO between your organization and Tableau Online, you follow these broad steps:

  1. Configure your organization as an identity provider in Salesforce.
  2. Adjust SAML settings in Tableau Online.
  3. Create a connected app in Salesforce to integrate with Tableau Online.
  4. Manage access to the connected app in Salesforce.
  5. Download and apply the identity provider metadata from Salesforce in Tableau Online.
  6. Test the SSO configuration by launching the application.
    As there is no substitute for hands-on practice, let us dive in and set this up:
  7. First, we need to configure Salesforce as an IdP. To do this, navigate to Identity Provider in Setup, as shown in the next screenshot:

Figure 7.23: Identity Provider section in Setup

  1. Click Enable Identity Provider, shown in the screenshot below, to enable your Salesforce org for identity:

Figure 7.24: Enabling Identity Provider

  1. Select the default certificate and click Save, as shown in Figure 7.25. Click Ok in the popup.

Figure 7.25: Selecting the certificate

  1. Your org is now enabled as an identity provider. Click Download Metadata, as shown in Figure 7.26, and save the file somewhere to get to it later.

Figure 7.26: Downloading metadata file
The second step involves enabling your Tableau Online site for SSO. You do this by following these steps:

  1. Log into your Tableau Online account.
  2. Navigate to Settings | Authentication, as shown in the following screenshot:

Figure 7.27: Authentication section in Tableau Online

  1. Click SAML and then Edit Connection. Then copy the two URLs Tableau Cloud entity ID and Assertion Consumer Service URL (ACS) to a text file. You will need these later.
    Now you will need to create a connected app in Salesforce for Tableau Cloud:
  2. First, navigate to App Manager in Setup, as shown in the screenshot below.

Figure 7.28: App Manager in Setup

  1. Click New Connected App at the top right.
  2. Now fill in the values carefully, as in Figure 7.29. Replace the start URL with the URL for your own Tableau Cloud site and Entity ID and ACS UR with the values you previously copied to a text file.

Figure 7.29: New Connected App configuration
Now you need to return to Tableau Cloud and import the Salesforce metadata:

  1. Navigate to Settings |Authentication, expand Edit connection and go to Step 4.
  2. Pick the metadata file you downloaded previously and click Apply as shown below:

Figure 7.30: Importing Salesforce metadata file

  1. In Step 6, select Authenticate using an inline frame, shown in the screenshot below:

Figure 7.31: SAML configuration option

  1. Under Default Authentication Type for Embedded Views pick SAML, as shown in Figure 7.32:

Figure 7.32: Default authentication type

  1. Now you can save.
    To work, the username (email) of the users using SSO must match between Salesforce and Tableau. So if you have not used the same username on the two systems, you will need to create matching user accounts on either or both systems to make the SSO work. Once you have done that, it will work.
    Note that there is now also an option of simply using Salesforce directly for authentication, which is easier to set up, but less general in its applicability. The method we have been through will work with any SAML-based IdP not just Salesforce.
More Details