AUSTIN, Texas, May 14, 2020 /PRNewswire/ --SparkCognition, a leading industrial artificial intelligence (AI) company, is pleased to announce that Japanese AI and Fintech company, MILIZE Co., Ltd. will offer Japanese financial institutions fraud detection and anti-money laundering solutions. These solutions will be built using the automated machine learning software of SparkCognition.

With the enormous increase of online payment, internet banking, and QR code payments, illegal use of credit cards is on the rise. However, there are not many Japanese companies that have introduced advanced solutions for fraud detection that currently exist internationally. In addition, financial authorities and institutions around the world are expected to report strengthened measures against money laundering in August 2020. As a result, taking these steps against money laundering has become an urgent management issue in Japanese financial institutions.

At one credit card company in South America, the ratio of fraudulent use to the total transactions reached about 20%, which reduced the profitability of the business. Therefore the company introduced a fraudulent transaction detection system that utilizes the AI technology of SparkCognition, which has extensive experience working with financial service clients. Though the credit card company did not have a team of data scientists, due to the ease with which analysts on staff were able to apply SparkCognition technology, accurate machine learning models were developed, tested, and operationalized within a few short weeks. As a result, it is now possible to detect fraudulent transactions with about 90% accuracy, which has led to a significant improvement in the credit card company's profitability.

Based on SparkCognition's international success in fielding machine learning systems in financial services, MILIZE will offer a fraud detection and anti-money laundering solution, built with SparkCognition AI technology, along with consulting services, development and operational assistance to local credit card companies, banks and other financial institutions. By submitting transaction data to a MILIZE-operated cloud service, financial institutions will be able to detect suspicious transactions without making large-scale investments in self-hosted infrastructure.

MILIZE makes full use of quantitative techniques, fintech, AI, and big data, and provides a large number of operational support solutions such as risk management, performance forecast, stock price forecast, and more, to a wide range of financial institutions. SparkCognition is a leading company in the field of artificial intelligence and provides AI solutions to companies and government agencies around the world.

To learn more about SparkCognition, visit http://www.sparkcognition.com.

About SparkCognition:

With award-winning machine learning technology, a multinational footprint, and expert teams focused on defense, IIoT, and finance, SparkCognition builds artificial intelligence systems to advance the most important interests of society. Our customers are trusted with protecting and advancing lives, infrastructure, and financial systems across the globe. They turn to SparkCognition to help them analyze complex data, empower decision-making, and transform human and industrial productivity. SparkCognition offers four main products:DarwinTM, DeepArmor, SparkPredict, and DeepNLPTM. With our leading-edge artificial intelligence platforms, our clients can adapt to a rapidly changing digital landscape and accelerate their business strategies. Learn more about SparkCognition's AI applications and why we've been featured in CNBC's 2017 Disruptor 50, and recognized three years in a row on CB Insights AI 100, by visiting http://www.sparkcognition.com.

For Media Inquiries:

Michelle SaabSparkCognitionVP, Marketing Communications [emailprotected] 512-956-5491

SOURCE SparkCognition

http://sparkcognition.com

Excerpt from:
SparkCognition and Milize to Offer Automated Machine Learning Solutions for Financial Institutions to the APAC Region - PRNewswire

The chaos and uncertainty surrounding the coronavirus pandemic have claimed an unlikely victim: the machine learning systems that are programmed to make sense of our online behavior.

The algorithms that recommend products on Amazon, for instance, are struggling to interpret our new lifestyles, MIT Technology Review reports.

And while machine learning tools are built to take in new data, they're typically not so robust that they can adapt as dramatically as needed.

For instance, MIT Tech reports that a company that detects credit card fraud needed to step in and tweak its algorithm to account for a surge of interest in gardening equipment and power tools.

An online retailer found that its AI was ordering stock that no longer matched with what was selling. And a firm that uses AI to recommend investments based on sentiment analysis of news stories was confused by the generally negative tone throughout the media.

"The situation is so volatile," Rael Cline, CEO of the algorithmic marketing consulting firm Nozzle, told MIT Tech.

"You're trying to optimize for toilet paper last week, and this week everyone wants to buy puzzles or gym equipment."

While some companies are dedicating more time and resources to manually steering their algorithms, others see this as an opportunity to improve.

"A pandemic like this is a perfect trigger to build better machine-learning models," Sharma said.

READ MORE: Our weird behavior during the pandemic is messing with AI models

This article was originally published by Futurism. Read the original article.

Continue reading here:
Our Behaviour in This Pandemic Has Seriously Confused AI Machine Learning Systems - ScienceAlert

LAKEWOOD, Ohio, May 14, 2020 /PRNewswire/ --Onix is proud to participate in the launch of Amazon Kendra, a highly accurate and easy to use enterprise search service powered by machine learning from Amazon Web Services (AWS).

Amazon Kendra delivers powerful natural language search capabilities to customer websites and applications so their end users can more easily find the information they need. When users ask a question, Amazon Kendra uses finely tuned machine learning algorithms to understand the context and return the most relevant results, whether that be a precise answer or an entire document.

"Search capabilities have evolved over the years. Users now expect the same experience they get from the semantic and natural language search engines and conversational interfaces they use in their personal lives," notes Onix President and CEO Tim Needles. "Powered by machine learning and natural language understanding, Amazon Kendra improves employee productivity by up to 25%. With more accurate enterprise search, Amazon Kendra opens new opportunities for keyword-based on-premises and SaaS search users to migrate to the cloud and avoid contract lock-ins."

Onix has been a leader in the enterprise search space since 2002. The company provides 1:1 consulting, planning, and deployment of search solutions for hundreds of clients with a team that includes 10 certified deployment engineers. Onix has won six prestigious awards for enterprise search and boasts a 98% Customer Satisfaction Rating.

About Onix

As a leading cloud solutions provider, Onix elevates customers with consulting services for cloud infrastructure, collaboration, devices, enterprise search and geospatial technology. Onix uses its ever-evolving expertise to achieve clients' strategic cloud computing goals.

Onix backs its strategic planning and deployment with incomparable ongoing service, training and support. It also offers its own suite of standalone products to solve specific business challenges, including OnSpend, a cloud billing and budget management software solution.

Headquartered in Lakewood, Ohio, Onix serves its customers with virtual teams in major metro areas, including Atlanta, Austin, San Francisco, Boston, Chicago and New York. Onix also has Canadian offices in Toronto, Montreal and Ottawa. Learn more at http://www.onixnet.com.

Contact: Robin Suttell Onix 216-801-4984 [emailprotected]

SOURCE Onix

Home

Read the rest here:
Onix To Help Organizations Uncover the Power of Machine Learning-Driven Search With Amazon Kendra - PRNewswire

Northern Trust has deployed machine learning models within its FX currency management solutions business, designed to enable greater oversight of thoughts of daily data points.

The solution has been developed in partnership with Lumint, an outsourced FX execution services provider, and will help buy-side firms reduce risk throughout the currency management lifecycle.

The technology utilised by the Robotic Oversight System (ROSY) for Northern Trust systematically cans newly arriving, anonymised data to identify anomalies across multi-dimensional data sets. It is also built on machine learning models developed byLumintusing a cloud platform that allows for highly efficient data processing.

In a data-intensive business, ROSY acts like an additional member of the team working around the clock to find and flag anomalies. The use of machine learning to detect data outliers enables us to provide increasingly robust and intuitive solutions to enhance our oversight and risk management, which can be particularly important in volatilemarkets, saidAndyLemon, head of currency management, Northern Trust.

Northern Trust announced astrategic partnership withLumintin 2018todeliver currency management services with portfolio, share class and lookthrough hedging solutions alongside transparency and analytics tools.

Northern Trusts deployment of ROSY amplifies the scalability of its already highly automated currency hedging operation; especially for the more sophisticated products such as look-through hedging offered to its global clients, addedAlexDunegan, CEO, Lumint.

The solution is the latest rollout of machine learning technology by Northern Trust, asthe bankcontinues to leverage new technologies across its businesses.

In August last year, thecustodiandeveloped a new pricing enginewithin its securities lending businessby utilising machine learning and advanced statistical technology.By using a hybrid cloud platform for highly efficient processing of data, Northern Trust will leverage a new algorithm that identifies strategic market data points from multiple asset classes and regions to project the demand for equities in the securities lending market.

The Chicago-based global custodian is underway rolling out new capabilities using robotic processing automation (RPA) and cognitive artificial intelligence (AI) within a framework called its Fund Accounting Optimisation Lab, in a bid to reduce manual entries and repetitive tasks when producing daily net asset value (NAV) for funds.

View post:
Northern Trust rolls out machine learning tech for FX management solutions - GlobalCustodian.com

Walmart provided more details on its new Express two-hour delivery service, piloted last month and on its way to nearly 2,000 stores.

As agility has become the key to success within a retail landscape extraordinarily disrupted by the spread of COVID-19, the company said it tested, released and scaled the initiative in just over two weeks.

As we continue to add new machine learning-driven capabilities like this in the future, as well as the corresponding customer experiences, well be able to iterate and scale quickly by leveraging the flexible technology platforms weve developed, Janey Whiteside, Walmart chief customer officer and Suresh Kumar, global technology officer and chief development officer, wrote in a company blog post.

The contactless delivery service employs machine learning to fulfill orders from nearly 2,000 stores, fulfilled by 74,000 personal shoppers. Developed by the companys in-house global technology team, the system accounts for such variables as order quantity, staffing levels, the types of delivery vehicles available, and estimated route length between a store and home.

See also: How the Coronavirus Will Shape Retail Over the Next 35 Years

It also pulls in weather data to account for delivery speeds, and Whiteside and Kumar said its consistently refining its estimates for future orders.

Consumers must pay an additional $10, on top of any other delivery charges, to take advantage of the service.

Separately. Walmartannounced it's paying out another $390 million in cash bonuses to its U.S. hourly associates as a way to recognize their efforts during the spread of COVID-19.

Full-time associates employed as of June 5 will receive $300 while part-time and temporary associates will receive $150, paid out on June 25. Associates in stores, clubs, supply chain and offices, drivers, and assistant managers in stores and clubs are all included.

Walmart and Sams Club associates continue to do remarkable work, and its important we reward and appreciate them, said John Furner, president and CEO of Walmart U.S., in a statement. All across the country, theyre providing Americans with the food, medicine and supplies they need, while going above and beyond the normal scope of their jobs diligently sanitizing their facilities, making customers and members feel safe and welcome, and handling difficult situations with professionalism and grace.

The retailer has committed more than $935 million in bonuses for associates so far this year.

See also: Walmart Expands No-Contact Transactions During COVID-19

See original here:
How is Walmart Express Delivery Nailing that 2-Hour Window? Machine Learning - Retail Info Systems News

In one of the most revealing research papers written recent times, the researchers from Cornell Tech and Facebook AI quash the hype around the success of machine learning. They opine and even demonstrate that the trend appears to be overstated. In other words, the so-called cutting edge research or benchmark work perform similarly to one another even if they are a decade apart. In other words, the authors believe that metric learning algorithms have not made spectacular progress.

In this work, the authors try to demonstrate the significance of assessing algorithms more diligently and how few practices can help reflect ML success in reality.

Over the past decade, deep convolutional networks have made tremendous progress. Their application in computer vision is almost everywhere; from classification to segmentation to object detection and even generative models. But is the metric evaluation carried out to track this progress has been leakproof? Are the techniques employed werent affected by the improvement in deep learning methods?

The goal of metric learning is to map data to an embedding space, where similar data are close together, and the rest are far apart. So, the authors begin with the notion that the deep networks have had a similar effect on metric learning. And, the combination of the two is known as deep metric learning.

The authors then examined flaws in the current research papers, including the problem of unfair comparisons and the weaknesses of commonly used accuracy metrics. They then propose a training and evaluation protocol that addresses these flaws and then run experiments on a variety of loss functions.

For instance, one benchmark paper in 2017, wrote the authors, used ResNet50, and then claimed huge performance gains. But the competing methods used GoogleNet, which has significantly lower initial accuracies. Therefore, the authors conclude that much of the performance gain likely came from the choice of network architecture, and not their proposed method. Practices such as these can put ML on headlines, but when we look at how much of these state-of-the-art models are really deployed, the reality is not that impressive.

The authors underline the importance of keeping the parameters constant if one has to prove that a certain new algorithm outperforms its contemporaries.

To carry out the evaluations, the authors introduce settings that cover the following:

As shown in the above plot, the trends, in reality, arent that far from the previous related works and this indicates that those who claim a dramatic improvement might not have been fair in their evaluation.

If a paper attempts to explain the performance gains of its proposed method, and it turns out that those performance gains are non-existent, then their explanation must be invalid as well.

The results show that when hyperparameters are properly tuned via cross-validation, most methods perform similarly to one another. This work, believe the authors, will lead to more investigation into the relationship between hyperparameters and datasets, and the factors related to particular dataset/architecture combinations.

According to the authors, this work exposes the following:

The authors conclude that if proper machine learning practices are followed, then the results of metric learning papers will better reflect reality, and can lead to better works in most impactful domains like self-supervised learning.

comments

More here:
Reality Of Metrics: Is Machine Learning Success Overhyped? - Analytics India Magazine