Squark

1.) The company that produces Squark Seer, most powerful AI predictive tool available, distinguished by its use of automated machine learning (AutoML) to achieve completely codeless operation. See www.squarkai.com.

2.) In particle physics, the hypothetical supersymmetric boson counterpart of a quark, with spin 0.

Max F1 Threshold

F1 is a score between 1 (best) and zero (worst) that shows how well a classification algorithm did at training on your dataset. It is a check different from accuracy that measures how well the model performed at identifying the differences among groups. For instance, if you are classifying 100 types of wine – 99 red and one white – and your model predicted 100 are red, then it is 99% accurate. But the high accuracy veils the model’s inability to detect the difference between red and white wines.

F1 is particularly revelatory when there are imbalances in class frequency, as in the wine example. F1 calculations consider both Precision and Recall in the model:

Precision = How likely is a positive classification to be correct? = True Positives/(True Positives + False Positives)

Recall = How likely is the classifier to detect a positive? = True Positives/(True Positives + False Negatives)

F1 = 2 * ((Precision * Recall) / (Precision + Recall))

Max F1 threshold is the cut-off point for probabilities in predictions. When a row’s P1 (will occur) value is at or above the Max F1, the outcome will be predicted to happen in the future. If a row’s P0 (won’t occur) value is below the Max F1, the outcome will be predicted not to happen.  This explains why the cutoff point is not always 50% as you might expect.

The optimal F1 threshold is approximately 1/2 the F1 score that it achieves. This gives you some intuition. The optimal threshold will never be more than .5. If your F1 is .5 and the threshold is .5, then you should expect to improve F1 by lowering the threshold. On the other hand, if the F1 were .5 and the threshold were .1, you should probably increase the threshold to improve F1.

Remember the max f1 threshold is not the same as the model’s f1 score (found in the advanced view). They are related but different as described above.

Can AI Help Retail Store Salespeople Sell More?

The best retail sales people excel because they attract customers, serve them well, and keep them coming back. They understand individual tastes and show complementary styles and accessories, boosting sales volume and customer satisfaction at the same time. Underlying this ability to perform on the floor are memorization of inventory, diligent work on outreach, and constant networking to expand clientele. You are probably thinking of your favorite professional right now—the one who can sell an entire ensemble to a long-time customer while helping two walk-ins miraculously “find” items they love.

AI is not going to replace people like these. It will augment their abilities to sell even more, and it will help salespeople with lesser skill to be more like them. Here’s how.

Get Them In
AI in the back office will enable ever-more-personalized messages to be sent to prospects and customers with compelling reasons to make a store visit. Machine learning allows buying patterns and trends to be predictions, as opposed to reactions. Without programming, AI algorithms can be tapped to show affinities and cross-sell opportunities with startling accuracy. A personal note from a with exciting content sent (automatically) from a sales professional is much more likely to prompt a visit than a generalized message. Salespeople get the advantage of outreach without consuming selling or personal time.

Treat Them Right
In-store selling tools can take advantage of AI in real time to offer suggestions on colors, patterns, compatible accessories, and sell-along items with knowledge of available inventory. Attractive assortments are simple to present to the buyer. This increases sales of available SKUs and reduces the time spent per visit—with better customer satisfaction. That is a recipe for better commissions.

Bring Them Back
Re-engagement cements the value of past, pleasant shopping experiences. AI makes it simpler not only to remind customers of items they’ve seen, but also suggest new merchandise choices. Here is where the predictive abilities of machine learning can amplify the seeming clairvoyance of top sellers and add some of that talent for new salespeople. By focusing correctly on sales by a person, to a person, AI for in-store retail can be effective while avoiding the “creepy” factor of behavioral online ads.

Make It Exciting
AI continues to help differentiate in-store retail experiences from online shopping. Real time, internet-of-things, augmented reality—driven by machine learning—is already being incorporated on the sales floor. But salespeople and inventory are the core reasons that stores draw traffic. Ironically, the primary benefit of Artificial Intelligence for retail stores will be helping real people sell, in person, to their customers.

Consider the Future
AI can create a new world for in-store retail that brings together machine intelligence with human intelligence to make the AI-augmented salesperson a reality. Additionally, grand orchestrations of AI-powered and data-informed store operations and shopper experiences are possible. Winners will be the retailers who conjoin the best of AI with the irreplaceable human elements shoppers will always seek.