Setting up and managing course analytics and reporting in Moodle involves configuring a set of tools and features that allow instructors and administrators to track and analyze student activity, progress, and outcomes within a course. Moodle has built-in analytics tools, along with some advanced reporting plugins that can be enabled to provide detailed insights.

Here’s how to set up and manage course analytics and reporting in Moodle:

1. Enable Course Analytics

Moodle provides a Course Analytics feature, which helps instructors understand how students are interacting with course materials.

Steps to enable:

1. Log in as an administrator.
2. Navigate to the Administration block.
3. Click on Site administration → Advanced features.
4. Ensure that Analytics is enabled. If not, check the box to enable it.
5. Next, go to Site administration → Analytics → Manage analytics models.
6. Enable an analytics model if it’s not already active (Moodle typically has predefined models like “Basic Course Completion”).

Once enabled, Moodle will start gathering data on student activity and will generate reports based on predefined models, such as student progress, predicted completion, and dropout risk.

2. Configure and Customize Analytics Models

Moodle uses Analytics Models to predict and assess student progress based on activity data. These models include prediction of course completion, engagement levels, and risk of dropping out.

Steps to configure models:

1. Navigate to Site administration → Analytics → Manage analytics models.
2. You will see the default models (such as Basic course completion model). You can edit these or add new models.
3. For new models, select Add new model. You’ll need to define the model type (e.g., course completion, engagement) and set conditions based on user actions like time spent, activities completed, etc.
4. You can define thresholds and weightings to help the system assess risk or predict success.

3. Generate Reports for Instructors

Instructors can access reports related to their courses to track student performance and engagement.

Steps for instructors:

1. Inside a course, navigate to the Course administration block.
2. Click Reports → Activity completion to view a list of students and their progress towards completing specific activities.
3. You can also go to Reports → Course participation to get an overview of student activity levels in terms of forum posts, quiz attempts, and other activities.
4. Under Grades, instructors can review the Gradebook for detailed insights into individual student performance.

4. Use the Completion Tracking Feature

Moodle’s Completion Tracking allows administrators and instructors to define activities and resources that need to be completed. This helps in tracking whether students have completed key activities for certification or progression.

Steps to enable Completion Tracking:

1. Navigate to Site administration → Advanced features and enable Completion tracking.
2. For each activity, go to Edit settings and set the Activity completion options, specifying what conditions must be met for the activity to be considered “complete” (e.g., viewing, submitting, scoring a certain percentage).
3. Instructors can then access the Activity completion report to track how students are doing in terms of completing required activities.

5. Utilize Plugins for Extended Reporting

Moodle has a variety of reporting plugins that can be added to extend the capabilities of course analytics and reporting. Some popular plugins include:

• Configurable Reports: This plugin allows administrators to create custom reports with filters, displaying data in tables or charts.
• IntelliBoard: A powerful external plugin that integrates with Moodle and provides advanced analytics and reporting.
• Learning Analytics (LAP): A plugin for predictive analytics that helps monitor at-risk students and predict course outcomes.

To install plugins:

1. Go to Site administration → Plugins → Install plugins.
2. Browse for the plugin, upload it, and follow the installation process.
3. After installation, navigate to Site administration → Reports to configure the plugin settings.

6. Access Student Activity Logs

For detailed insights into student activity, you can access the Logs for any course. This can help in identifying which students are actively engaging with the course material, which activities they are completing, and at what times.

Steps to view activity logs:

1. Inside the course, go to Course administration → Reports → Logs.
2. You can filter the logs by date range, activity type, and user. This is useful for tracking interactions or identifying students who might need additional support.

7. Schedule Reports for Automated Delivery

You can set up automated reporting for regular updates on student progress or performance.

Steps to schedule reports:

1. Go to Site administration → Reports → Scheduled reports.
2. Select the report you want to schedule, and configure the frequency (e.g., daily, weekly, monthly) and the delivery method (e.g., email).

8. Exporting Reports

Moodle allows you to export reports in various formats, such as CSV, Excel, or PDF, which can be shared with stakeholders or used for further analysis.

Steps to export:

1. Once you’ve generated the desired report (e.g., grades, activity completion), you can click the Export button (typically at the bottom or top of the report).
2. Select the format (CSV, Excel, PDF) and click to download the report.

Conclusion

By enabling and configuring analytics tools, creating custom reports, and using plugins, Moodle can become a powerful system for tracking and analyzing student progress. Regular use of these tools will allow you to identify at-risk students, monitor engagement, and ensure your courses are achieving their intended outcomes.

The post How to set up and manage course analytics and reporting in Moodle? appeared first on Artificial Intelligence.

The analysis of a large volume of data is already an indispensable part of the decision-making process for any business, regardless of its volume. Big data is used to resolve routine problems, such as improving the conversion rate or to achieve customer loyalty for an eCommerce business. But did you know that you can also use it to predict situations before they occur? This is the added value of predictive analytics, the use of big data to anticipate user behaviour based on historical data and act accordingly to optimise sales.

For online businesses, periodically performing predictive analytics is synonymous with improving your understanding of the customer and identifying changes in the market before they happen. The predictive models extract patterns from historical and transactional data to identify risks and opportunities. Self-learning software will automatically analyse the data at hand and offer solutions for future problems. This will allow you to design new sales strategies to adapt to changes and boost profit growth.

Specifically, predictive analytics allows you to:

1. Anticipate market trends.

Based on data from previous periods, predictive analytics will identify the points of maximum and minimum demand that the company might experience throughout the year. This allows eCommerce businesses to react before their competition by preparing a good customer acquisition campaign and having enough stock on hand to meet demand. They can also design a dynamic pricing strategy to optimise sales.

Along the same lines, dynamic pricing relies on predictive analytics to adjust prices to the needs of the market. Through tools like the dynamic pricing tool from Minderest, more than 20 different KPIs can be analysed automatically to establish the best prices for your products and services while always taking into account historical data and the results of decisions made in the past.

1. Design personalised offers.

Predictive analytics allow you to predict which offers will be most effective according to the specific characteristics of each client. With good segmentation, you can predict future behaviour and attitudes for each user group based on how they have acted in the past and offer them only those products are services which are of interest to them. The key to achieving this can be found in the analysis of the information about what each client bought, how much they spent, their location, the channel used, and other key performance indicators.

1. Optimise resources in the sales

Through predictive analytics, you can also predict the behaviour of your clients throughout the sales funnel. It’s possible to detect whether there’s a risk of them abandoning their commercial relationship with the eCommerce business as well as if they’re open to making new purchases in the future. In short, you can identify the most profitable customers, those which should receive more attention from the company.

Despite its many benefits, CEOs and marketing managers should keep in mind that, since it’s based on historical data, predictive analytics can’t always find an explanation for changes in the behaviour of buyers or competitors. If a new element that changes the dynamics of the market comes into play, such as the emergence of new virtual assistants for purchasing like Alexa, this tool won’t be able to predict it.

Analysing the competition’s strategy

In addition to knowing the market situation, it’s important to be aware of the strategies the competition is using. In this sense, one key factor is monitoring the prices and promotions offered by each competitor to determine their profit margin and predict the actions they could take in the coming months. This is another offshoot of predictive analytics that allows an eCommerce business to pull ahead of its direct competitors.

Through price tracking tools for retailers, it’s possible to detect any price changes from other companies in the sector, whether they are medium- or long-term changes or sporadic discounts. As a consequence, you can identify their campaigns, promotions, and the timeframe in which these are carried out.

As a whole, the incorporation of big data as a differentiating factor in decision making becomes a competitive advantage for those businesses that are looking to increase their sales.

The post Big Data: The Role of Predictive Analytics in Sales Growth appeared first on Artificial Intelligence.

Microsoft Azure customers worldwide now gain access to ProcessMiner’s AI platform to take advantage of the scalability, reliability and agility of Microsoft Azure to drive application development and shape business strategies.

ProcessMiner, an Artificial Intelligence platform for manufacturing, announced its platform is live in the Microsoft Commercial Marketplace. Based in Atlanta GA, ProcessMiner delivers real-time systems monitoring, predictive analytics, and recommendation solutions for manufacturers.

Continuous manufacturing processes are highly complex, and the ProcessMiner platform combines the strengths of data science and machine learning to help improve product quality. Defects, errors, scrap-rates and sub grade products are expensive to any manufacturing operations and ProcessMiner’s turn-key platform identifies and helps fix underlying causes of product quality degradation. Any manufacturer with continuous improvement goals can benefit from the information ProcessMiner delivers its operators through highly intuitive user-interfaces. Among the system’s benefits is a lower cost of operations through energy savings and reductions in raw materials. Additionally, Product Quality improvement lessens waste and improves product margins and production throughput.

Microsoft Azure is a cloud platform created by Microsoft for building, testing, deploying, and managing applications and services through Microsoft managed data centers. Commonly referred to as Cloud Computing it provides users and customers software-as-a-service (SaaS), platform-as-a-service (PaaS), and infrastructure-as-a-service (IaaS) services and supports many different programming language tools and frameworks, including both Microsoft-specific and third-party software systems. This allows customers who are interested in using ProcessMiner’s software the ability to procure the software directly in the Microsoft Commercial Marketplace.

“We are very excited about growing our operating reach with acceptance into the Azure Marketplace,” said Karim Pourak, Co-founder and CEO of ProcessMiner. “Historically, we’ve come across interested manufacturing companies looking to deploy our software for their business, but they were hamstrung because our operating environment was limited to one cloud services provider”. Pourak added, “Now that our platform is hosted with multiple cloud service providers, we’ve lifted that restriction allowing us to scale more rapidly.” he continued “Thanks to the marketing features of Azure, we expect to broaden our awareness to manufacturers shopping for Artificial Intelligence.”

“The Microsoft Commercial Marketplace lets customers worldwide discover, try, purchase and deploy software solutions that are certified and optimized to run on Azure”, said Diego Tamburini, Principal Industry Manager for Manufacturing, at Microsoft Corp. “The Microsoft Commercial Marketplace helps solutions like ProcessMiner reach more customers and markets.”

The post ProcessMinerTM Now Available in the Microsoft Azure Marketplace appeared first on Artificial Intelligence.

Align Capital Partners announced the closing of a third strategic add-on for its utility intelligence platform E Source. TROVE Predictive Data Science is a leading provider of predictive analytics solutions for the utility industry. TROVE’s talented team of data scientists and engineers have developed artificial intelligence software to help clients make better, data-driven decisions to improve their bottom line, reduce operational risk, and increase customer satisfaction.

Based in Buffalo, New York, TROVE helps utilities use data to optimize decision making. TROVE provides forward thinking utilities with data to forecast the impact of electric vehicle adoption, down to the transformer level. TROVE also leverages data and predictive science to forecast vegetation growth around power lines so utilities can optimize their vegetation management planning and reduce the risk of wildfires. “The customers and end markets we serve are driven by a growing need for product and program innovation,” said Ted Schultz, CEO of TROVE. “With the combination of our talented teams, data, and domain expertise, we are uniquely positioned to meet these and future needs.”

E Source provides subscription and consulting-based services for thousands of utility employees and senior leaders across North America. “Our acquisition of TROVE allows us to apply their sophisticated predictive data science to our proprietary utility data sets, best practice research, and consulting engagements,” said E Source CEO Wayne Greenberg. “They have had incredible success using advanced AI software to deliver big wins quickly for some of the largest utilities in the U.S. The opportunities for collaboration are endless and we welcome the TROVE team into E Source.”

The TROVE acquisition is a transformational moment for the Company, representing continued efforts to provide a broad offering of technology-enabled, tactical solutions to help utilities make the best data-driven decisions. ACP acquired E Source in June of 2019 and last week announced the Company’s acquisition of smart meter and smart city advisory firm, UtiliWorks Consulting. Both companies will be united under the E Source brand in the months ahead.

“The talents and capabilities of E Source, TROVE, and UtiliWorks are a powerful combination,” said Rob Langley, ACP Managing Partner and Co-Founder. “Running a utility is exceedingly complex. Technology innovation, environmental sustainability, increased customer awareness, and decentralized power generation are just a few of the challenges facing today’s utility leaders. These acquisitions create an interconnected, hard-to-replicate model enhancing E Source’s position as a thought leader fully dedicated to the utility market.”

Operating Partner Dave Perotti, Vice President Matt Iodice, and Associate Corey Roe worked alongside Mr. Langley on the transaction.

The post Align Capital Partners’ E Source Platform Acquires TROVE Predictive Data Science appeared first on Artificial Intelligence.

December 11, 2019 – Twenty-two percent of healthcare organizations use a software platform that provides artificial intelligence capability, according to a recent report from HealthLeaders Media.

This is an eight-point increase from 2017, the organization noted, indicating that AI use is steadily rising among health systems.

Thirty-one percent said they plan to have AI capability within the next three years, and 63 percent said their organizations plan to increase their investments in analytics technologies within the next three years.

HealthLeaders surveyed 128 individuals representing different healthcare provider organizations, aiming to measure AI and analytics use across the healthcare ecosystem.

Providers see a wide range of applications for AI, with 81 percent of respondents saying their organizations currently or plan to apply the technology to clinical data, 72 percent to financial data, and 59 percent to patient data.

Organizations also see potential in analytics capabilities. Sixty-three percent of respondents said they plan to increase their investments in analytics, while 35 percent said their investments would stay the same. Just two percent of respondents said their investments would decrease.

Health systems are also leveraging analytics strategies to extract insights from various sources of information. The report found that 78 percent of respondents said they use descriptive analytics for financial data, while 81 percent said they leverage descriptive analytics for their clinical data.

However, fewer participants use predictive capabilities for financial and clinical data analytics. Sixty-four percent said they apply predictive analytics to their financial data and 52 percent reported using predictive capabilities for clinical data.

Analytics investments have led to a strong return on investment for organizations: Forty-one percent describe their organizations’ return on investment on analytics as acceptable, while 30 percent describe analytics ROI as good and 14 percent describe it as very good.

Just 16 percent of respondents describe their analytics ROI as poor or very poor.

When asked about the most significant challenges in performing analytics, most respondents named issues involving human skills and staffing.

Forty-eight percent of participants see the need for timely analysis as the top challenge in performing analytics over the next three years. Forty-six percent said overcoming insufficient analytics skills would be the most challenging, while thirty-seven percent view insufficient funding as their biggest issue.

In addition to revealing staff education and training issues, these barriers also reflect investment challenges, researchers noted.

“Two of the top three tactical challenges are either indirectly or directly related to financial resources,” the report stated.

“For example, the solution to solving the problem of insufficient skills in analytics is investment in training or adding analytics staff, and insufficient funding in light of other priorities needs no explanation.”

These findings mirror statements from a February 2019 Kaufman Hall report, which said that financial executives should expand the scope of their responsibilities and investments in order to keep up with new technologies.

“Given the demands of the changing business environment, healthcare CFOs nationwide should be critically examining the role they and their finance teams play in their organizations. A singular focus on directing or managing financial operations and the related control/monitoring function is not sufficient going forward,” the report concluded.

“Finance executives must be integral to the development, execution, and monitoring of the organization’s vision and strategy, and be armed with the full breadth of data and analytics required for performance management in healthcare.”

Organizations also cited data-related challenges in performing analytics. Half of respondents said integrating internal clinical and financial data is a top challenge, and 46 percent said integrating external clinical and financial data is a major barrier.

The third most-cited challenge was improving EHR interoperability, with 43 percent of respondents naming this as a major barrier to building analytics capabilities.

Looking ahead, 62 percent of respondents said that the most promising area of analytics development would be clinical best practices, while 54 percent cited real-time delivery of actionable information as the most promising area of analytics.

This indicates that most health systems are interested in using analytics technologies to enhance care delivery and outcomes. Thirty-nine percent of participants also named improved quality of care as the primary goal they would expect to achieve through integrating financial and clinical data.

In September 2019, a survey from HIMSS Analytics and Dimensional Insight yielded similar results, showing that the future of the industry will focus on quality rather than quantity.

“As healthcare organizations move to value-based payment models, they are finding that focusing on clinical metrics, including readmission rates, infection control, and patient outcome improvements is critical for success,” George Dealy, vice president of healthcare solutions at Dimensional Insight, said at the time. 

“Analytics provides tremendous insight into these areas and can benefit healthcare organizations that are navigating this transition.”

The post 22% of Orgs Currently Use Artificial Intelligence Software appeared first on Artificial Intelligence.

November 08, 2019 – Machine learning methods could accurately identify cancerous esophagus tissue on microscopy images without the time-consuming manual data input that is required for current methods, according to a study published in JAMA Network Open.

Researchers at Dartmouth and Dartmouth-Hitchcock Norris Cotton Cancer Center have developed an innovative machine learning approach that automatically learns clinically important regions on whole-slide images to classify them.

Histopathology image analysis requires a manual annotation process that outlines the regions of interest on a high-resolution whole slide image to train the computer model. Although the method is advanced, the process is still tedious.

“Data annotation is the most time-consuming and laborious bottleneck in developing modern deep learning methods,” said Saeed Hassanpour, PhD, lead author of the study.

“Our study shows that deep learning models for histopathology slides analysis can be trained with labels only at the tissue level, thus removing the need for high-cost data annotation and creating new opportunities for expanding the application of deep learning in digital pathology.”

The team tested their method for identifying cancerous and precancerous esophagus tissue on high-resolution microscopy images without training on region-of-interest annotations. Researchers then applied the network to Barrett esophagus and esophageal adenocarcinoma detection and found that their method achieved better results than the traditional method.

“Our new approach outperformed the current state-of-the-art approach that requires these detailed annotations for its training,” said Hassanpour.

“The result is significant because our method is based solely on tissue-level annotations, unlike existing methods that are based on manually annotated regions.”

Machine learning technology has consistently demonstrated its potential to improve diagnostics and care management. Recently, a team of researchers used machine learning tools to accurately predict patients with cancer who were at high risk of six-month mortality, which could help clinicians engage in timely conversations with their patients.

“Our findings demonstrated that machine learning algorithms can predict a patient’s risk of short-term mortality with good discrimination and PPV. Such a tool could be very useful in aiding clinicians’ risk assessments for patients with cancer as well as serving as a point-of-care prompt to consider discussions about goals and end-of-life preferences,” the researchers stated.

“Machine learning algorithms can be relatively easily retrained to account for emerging cancer survival patterns. As computational capacity and the availability of structured genetic and molecular information increase, we expect that predictive performance will increase and there may be a further impetus to implement similar tools in practice.”

The research team on the esophageal study believes that this new machine learning approach could improve cancer diagnosis and care.

“Our method would facilitate a more extensive range of research on analyzing histopathology images that were previously not possible due to the lack of detailed annotations,” Hassanpour concluded.

“Clinical deployment of such systems could assist pathologists in reading histopathology slides more accurately and efficiently, which is a critical task for the cancer diagnosis, predicting prognosis, and treatment of cancer patients.”

In future work, the team plans to further validate the model by testing it on data from other institutions and running prospective clinical trials. Additionally, the group will apply the method to histological images of other types of tumors and lesions that have limited training data.

The post Machine Learning Tool Accurately Diagnoses Esophageal Cancer appeared first on Artificial Intelligence.