Machine vs Human : Artificial ? Yes, Intelligence ? No

Machine vs Human : Artificial ? Yes, Intelligence ? No

Machine Learning (ML) is becoming ubiquitous in the business world, leaving us with the impression that humans will shortly be replaced by Artificial Intelligence (AI). While at first glance this seems to be true, upon closer inspection this is not at all the case. Certainly, AI-powered automation will continue to eliminate jobs, such as Amazon’s 75,000 robots used to optimize the company’s warehouse logistics, but this is not new. It is always cheaper and more efficient for robots to move packages around a warehouse. So let’s say that humans are being replaced by automation rather than AI.

On the other hand, AI, and ML in particular help us analyze large quantities of data (or big data if you prefer buzz words). How exactly does ML work? Who does the learning in Machine Learning? The answer is: humans. Yes, Machine Learning algorithms rely on datasets used for learning, which are created and generated by humans. The more complex the problem, the more data the algorithm needs. This is an aspect of AI that we do not talk about very often, since it is not very fashionable. It puts the focus back on artificial, rather than intelligence. In fact, Machine Learning is a form of what we call weak AI. Instead of saying that it is not intelligent, we prefer to say that it is of limited intelligence. Imagine saying to someone that they are of limited intelligence? In fact, this is another way of saying that they are in fact unintelligent. The same parallel can be drawn with computers.

Will AI replace humans?

No, as you have understood, we will always need humans to create datasets and generate data used to teach the machines. For now, AI is not destroying jobs. Rather, it is increasing our capacity for analysis and can even create jobs. Like all technological revolutions, it will change the way we live, learn and work.

Written by Bernard EUVERTE, CEO founder of WorkIT Software

FASHION: WORKIT @ TRAFFIC

FASHION: WORKIT @ TRAFFIC

On April 4th and 5th WorkIT visited the TraFFic trade show. This is the second year that the show was organized at Carreau du Temple in Paris. TraFFic helps bring together brands/designers and companies working in domains such as Marketing, Tech and Human Resources. Its first aim is to help brands discover technologies and connect with companies that can help them grow and evolve. Its second aim is to facilitate an exchange between the different actors in order to facilitate business opportunities. Finally, its third goal is to promote fashion tech innovation.

We visited the show in order to gain further insights into what is new and innovative on the FashionTech scene. Not surprisingly, there was a strong focus on Artificial Intelligence, with a variety of companies proposing solutions that are capitalizing on these technologies. We were pleasantly surprised to see how the sector is becoming transformed by Machine Learning algorithms that are able to analyze millions of fashion images and descriptions in order to find similar products, predict trends or offer a more personalized on-line shopping experience. This is in line with our work at WorkIT, where we are using state-of-the-art Machine Learning algorithms to transform and advance pricing intelligence for fashion products. One thing is for sure – AI is here to stay, and its impact on the retail sector will only continue to grow and evolve.

Machine Learning

Machine Learning

With the constant growth of the E-commerce worldwide market, competitive intelligence has become an increasingly complex task due to:

  • An increasing volume of products on sale
  • A high inventory turnover rate, implying a large quantity of products to monitor in a limited time frame
  • A diverse range of e-commerce products  (electronics, fashion, food, etc)
  • The emergence of new e-commerce websites, as well as the transition of traditional retailers to E-business, combining physical and online sale points

In such a context, how can e-commerce retailers position themselves with respect to the competition? For over a decade, we have been supporting our clients with our competitive intelligence solutions. Recognized for the quality of our data, we are constantly innovating to improve our algorithms and adapt to the rapidly changing e-commerce ecosystem.  Using cutting-edge Machine Learning models, we are building our next generation of algorithms to extensively cover the e-commerce market.

One of our most important challenges is what we call matching. This consists of identifying the product being sold in each offer. For example, if we consider an offer titled black Apple Iphone 7 256 Go, it’s easy for a human to identify that this offer corresponds to an Apple (brand) smartphone (product type). More precisely, it refers to a black (color) IPhone 7 (model) with 256 GB (storage capacity). But how can a machine accomplish such a task? We could teach a machine to learn to recognize key product characteristics, such as its storage capacity, color and model,  as in the smartphone example. Similarly, different features need to be learned to identify a particular dress, such as, amongst others, its length, collar type and fabric. For bed linens, the key identifying factor would more likely be the thread count. We would also need to teach the machine the different ways that we can describe the same product, e.g., sports shoes can also be called running shoes, sneakers or trainers.

So as you can imagine, in a universe where domain-dependent knowledge is required, it would be very expensive to manually cover the entire e-commerce market.  It is thus vital to have intelligent algorithms that are able to learn inherent product characteristics across the whole spectrum of e-commerce products.

Based on text (description, title, brand, color, size, etc.) and image data , our algorithms learn to identify the products associated to particular offers. The first crucial step is what we call feature engineering. This consists of finding the best mathematical representation that contains the semantics of the offers. The representation comes in the form of vectors and is obtained by digesting images and textual data associated to the offers.

The power of our algorithms therefore depends on our ability to find the best vector representations of the offers.  On the one hand, we implement Natural Language Processing (NLP) methods to preprocess and transform textual data.  On the other hand, we use Deep Learning algorithms to encode images into feature vectors. This results in two independent mathematical representations for the text and the image. Using both representations and mathematical methods to combine them, we are able to match similar offers based on the similarity of their vector representations.

Before the matching process, we start with a preliminary automatic categorisation step. This step serves two purposes: we end up with an organized catalog of products and we only look for potential offer matches  within the same category.

Given that data quality has always been our number one priority, we have opted for an Active Learning approach. Instead of blindly relying on what machine learning models predict, we expose the predictions to human matchers. Initially, all predictions must be validated by a human. After some feedback cycles, we will learn under which conditions we can trust the predictions, while keeping high value-added tasks for our quality control team. Finally, the method is called active learning because the model is constantly retrained using human feedback in order to improve its accuracy.

So, that was the first glimpse of the latest developments at WorkIT Software. This incursion into the Machine Learning world is a crucial step that allows us to be a leader in the competitive intelligence market and to provide our customers with  an ever growing catalog of e-commerce products

Article written by Felipe Aguirre Martinez
Lead Data Scientist at WorkIT Software – Doctor of Philosophy (PhD), Computer and Information Sciences