By Shai Cohen, VP Sales at

Machine Learning and predictive AI can learn from past behaviors and real-time data to provide a dynamic and, therefore, more accurate forecast. It’s no surprise that many companies have rushed to implement AI in their organization. According to an MIT Sloan review, 9 out of 10 agree that AI represents a business opportunity for their company. However, few have seen the benefits of AI in their business. In fact, 7 out of 10 companies reported that they have seen minimal or no impact from their AI implementation.

One of the key challenges in AI technology adoption is the translation of analyzed data into business value. There is a lot of information that is nice to know, and that can be presented in pretty dashboards, graphs, and notifications. Still, at the end of the day, information is only useful if it leads to actions that deliver business value.

Organizations should focus on closing the gap between ML generated information and tangible business value. For every business use case, it’s important to understand the story the data is telling and identify the relevant insights that you need to know in order to focus on the critical to dos for your business. 

Image:Brent Dykes, Effective Data StoryTelling 

For example, at Curve.Tech we use Machine Learning to help Sales & Supply Chain stakeholders make better decisions by identifying potential business risks early and suggesting possible solutions. Here are some examples:

  1. Optimized Inventory Levels – Real-time alerts on overstock and understock risks at the product, location, and client level, with suggestions for mitigation. React on time based on your lead time and the expected demand.
  2. Dynamic Lead Time Calculation – LT calculations based on actual behavior rather than predefined static categorization. Know your actual lead time to work better with your manufacturers and manage the risks of each one. Optimize stock based on the real behavior of your suppliers.
  3. Predict Impact of Supply Delays – Analyze the impact a delay in supply has on sales and see suggested actions based on inventory and client priorities. Make decisions early to mitigate risk and reduce impact.
  4. Predict Returns – Predict returns based on customer behavior and combine it as a factor for stock optimization to keep your overall inventory level accurate.
  5. Identify Trends Early – Alerts on emerging upward and downward sales trends at the product, category, and geographic levels. Adjust sales and marketing efforts, inventory, and location volumes accordingly to take advantage of new opportunities.
  6. Sales Forecast vs. Goals – Get input early in the quarter on how you are performing against your plan and budget. React on time and focus your efforts on where they are needed to meet your KPIs and stay on track.
  7. “What-If” Simulations: Based on factors that influence sales, simulate possible scenarios with actions within your control, such as price and marketing. Compare possibilities to find the best path of action.

In order to truly leverage AI, it’s important that businesses cut through the noise and consider the gap between the data, technology, and business value. When entering an AI project, make sure you start with the end goal in mind. Consider the business decisions you want to make and start working backward from there.

Do you want to hear more about how you can use machine learning for sales forecasting in your business? Reach out to us for a consultation at

By Tal Eden, Chief Data Scientist at


Machine Learning is the ability of computers or machines to learn without being explicitly programmed. Arthur Samuel

Supervised learning is a specific field of machine learning in which a machine learns to label data based on a set of prelabeled examples. Sales prediction is a specific example of supervised learning. We have a labeled data set of past sales, and we generate a prediction for future sales.

In the example of retailers – we want to infer the future sales volume of each product in each point of sale based on historical data such as past sales, item price, date (whether it is a holiday or not), etc. In the past several years, we have seen a spike in the number of businesses using such predictive components in their planning processes as technology gradually became more accessible.

One of the greatest adversaries of sales prediction (and of any prediction engine in general) are black swan events. The machine cannot reliably predict any longer because the historical (labeled) data is no longer relevant. For example, historical sales data after a financial crisis like the one that occurred after the collapse of Lehmann Brothers in 2008 can no longer serve as a basis for prediction because people have less money and therefore tend to buy less. The environment in which the predictive engine was created has changed so drastically that it has rendered the engine unusable. Another prominent example is the Coronavirus outbreak that we are currently experiencing.

Our machine cannot predict accurately because history is irrelevant; here, history cannot and does not repeat itself.

Sales have been altered completely – whether online or offline.

Fashion retailers have suffered a significant decrease in sales volume. A prominent example in this industry is Adidas; the German sportswear company reported that it expects first-quarter sales to drop by $1.14 billion in greater China. Like most fashion retail stores, they have had to close physical stores, and people are buying less sportswear and leisurewear.

While sales in the fashion industry have plummeted, sales in the online food industry are skyrocketing. According to Nielsen, last year, just 4% of grocery sales in the US came online. However, with people avoiding crowds or being quarantined, the alternative is to buy online. Downloads of Instacart, Walmart’s grocery app, and Shipt increased 218%, 160%, and 124%, respectively compared with the prior year.

Can we still predict?

Do not despair! Although times are changing, businesses who can adapt rapidly have the opportunity to make the best out of the crisis and leverage it for future growth. Below are a few suggestions on how to deal with this situation in terms of demand forecasts – and all its implications – sales, financial planning, orders, and deliveries?

  1. Understand the New World Order
    Create a comprehensive, real-time BI dashboard. You can see which products are seeing an increase or a decrease in sales. Walmart has reported an increase in sales for tops, whereas a decline in sales for bottoms (thank you video conferencing).
  2. Integrate external data sources – You need to understand how different events influence this new “order” – the number of infected people, whether schools have been closed or not, is there a curfew in place and more.
  3. Working without Historical Data
    When there is little historical data to rely on, data should be sampled at a higher frequency. If you were generating predictions on a monthly basis, you should switch to daily predictions, and if you were doing daily predictions, we recommend real-time analysis. 

    This will benefit the company twofold:
  • Information will be gained quicker
  • Sensitivity to changes will be higher even without long term predictions

Accordingly, we will need a different set of ACTIONS than those for long term predictions:

  1. Inventory: Your inventory strategy in times of crisis should be continuously changing based on data-driven insights. A few examples are mobilizing products intended for offline stores to online stores or making sure you have enough stock in locations in which the stock is likely to be consumed.
  2. Marketing strategy: Your marketing strategy should reflect the changing environment. Identify strong sellers, feature them, and use your marketing budget for them rather than “weaker” products or try to push products that display a strong negative trend before the trend sets a new baseline.
  3. Be ready to draw rapid insights and translate them to quick actions – When the environment is changing rapidly, businesses who cannot adapt in a timely fashion will be rendered irrelevant. You should be ready to make business-impacting decisions based on your new insights and predictions.

While we cannot predict the future reliably in times of uncertainty, we can draw meaningful conclusions regarding the rapidly changing environment.  This helps us harness the technology to help us identify immediate trends, plan our next steps, and how to weather the storm the best way possible.

Do you want to hear more about how you can use machine learning in your business? reach out to us for a consultation at

When it comes to operating retail sales at a high level in 2019, sales forecasting is critical to your business. Whether you run your business as a brick and mortar or operate strictly online, forecasting technology is a must-have if you want to keep up with your competitors in today’s age.
In the past, we have labored long and hard with sales and inventory forecasting through endless paperwork, spreadsheets, and of course, the cost of the labor to do the forecasting. More recently BI was helmed as an efficient means in which retailers can conduct sales forecasts tasks, however, that still only delivers intelligence based on business hindsight.
Today, businesses that are leading the pack have integrated smart forecasting technology allowing them to operate at with greater efficiency and speed while simultaneously cutting labor costs down dramatically.
So why is Sales Forecasting such an essential part of the retail industry today? Essentially, when done right it will deliver the following benefits for your organization.

  • Improved decision-making about the future
  • Reduction of sales pipeline and forecast risks
  • Alignment of sales quotas and revenue expectations
  • Reduction of time spent planning territory coverage and setting quota assignments
  • Benchmarks that can be used to assess trends in the future
  • Ability to focus on a sales team on high-revenue, high-profit sales pipeline opportunities, resulting in improved win rates

Here are three tips you can take advantage of today if you’re debating the value of new sales forecasting technology:

Leverage The Data You Have

You may think that you need to start collecting and organizing a ton of different metrics before you can really start to forecast your future sales trends effectively. Don’t worry, you don’t need to do a ton of work before getting started. You can use what you have today.
That being said, the greater the data you have, the more accurate your future sales forecasts will be, and you must weigh this against the result you need with the forecasting itself.

Clearer Data, Less Noise

When it comes to utilizing forecasting technology, you will get the best results when you have the right data. The great thing is with our solution Sales Prediction by Curve, you will be assisted in exactly what data is essential for the algorithms to provide clear forecasts.
Additionally, with frictionless sales forecasting, you don’t need to worry about the “behind the scenes” forecasting technology. The sophisticated solution was designed with retailers and sales teams in mind.
In other words, making data available to you should be the primary goal, while understanding the technology behind it shouldn’t set you or your team back.

Data Can Only Take You So Far

Having access to sales forecasts and product demand data is imperative, as described above, however, having a clear plan on how to effectively utilize your sales trends is equally important.
To effectively create a sales forecast action plan we recommend starting with the right set of questions:

  • What are you going to focus on?
  • What are you going to change?
  • In practical terms, what steps are involved?
  • What territories and targets are you going to give each salesperson or team?

Keep in mind that the main purpose of sales forecasting is to provide information that you can use to make intelligent business decisions.
For example, if your forecast indicates a 30% increase in sales of products or services you may wish to begin searching for larger business premises and/or increase additional stock on your hot items. Conversely, a forecast of excess stock or low sales can allow you to mitigate the effect by taking advance measures such as reducing expenses or reorienting your marketing efforts.

In Conclusion

For leading retailers, sales forecasting is not only crucial to surviving, but also to thrive. Not only will it allow you to predict upcoming sales trends accurately and efficiently, but it will allow you to manage product demand.
Over the next decade, the difference between businesses that advance to the next level and those that fall behind will be greatly based upon the businesses that adopt new technology systems in their business.
You can still get an upper hand on the competition by allowing forecasting technology to push your business forward today.

Inventory issues are a business owner’s worst nightmare.
Especially when you’re in a growth phase, and in the middle of expanding to meet customer demand, it can set back your sales team and impact your bottom line.
Whether you’re an e-commerce or brick-and-mortar store, inventory can get the best of you, and when it comes to inventory forecasting, the majority of retail business owners simply don’t know where to start. Failing to have a sales and inventory sales forecasting plan will usually lead to lost sales, time wasted running around in circles.
What’s the solution? Inventory forecasting.
Inventory forecasting assists businesses in optimizing their inventory purchasing what products to buy, how much to buy, and when to buy. Alternatively, it assists in knowing when it’s time to liquidate unsold inventory.
The key with inventory is understanding past trends to the past to predict the future sales potential. When a business is operating on a “what’s to come” basis rather than just focusing on what’s happening now, operations can run smoothly, especially with inventory.
Here are five reasons why inventory forecasting is essential for the success of your business:

  1. Better cash flow

Let’s face it. We’ve all been there. Cashflow is tight because we just made a huge inventory purchase. Then for the next few months, we begin to get anxious as to why it’s not moving fast enough. When you optimize your business with inventory forecasting, you can accurately predict how much inventory to buy every time so you’re not put in a tight spot with cash flow for your business. And in today’s rapidly changing sales landscape, that makes all the difference.

  1. More time

It is not easy running an entire business. Most days, there are several fires to put out at once, locations to run, customers to keep, suppliers to manage and employees to maintain. You’re busy enough trying to deal with daily operations. Investing time in sales foresight is yet another issue on your mile-long list that is eating away at your time. Forecasting involves various preventative measures so you don’t have to spend hours constantly putting out inventory fires. By making it a part of your business operation, you’re ensuring that you will have enough time to run your business actively, instead of reactively.

  1. Simplify operations

With proper forecasting strategies and procedures, you can cut out a lot of complications and processes that are slowing down operations. Inventory forecasting allows simplicity to take over so you can operate on a step-by-step plan instead of jumping all over the place in your inventory tracking.

  1. Save on labor with software

With the ever-increasing technology, businesses are able to cut back on unnecessary labor costs. If an algorithm can do it in way that’s quicker and unbiased, then why hire an employee? Inventory forecasting software is able to complete the simplest tasks to even the extremely sophisticated. One of the more sophisticated tasks, for instance, is predicting what products a customer is likely to buy if they buy a specific one. (eg. if a customer buys product A there is a 93% chance they will also buy product B).

  1. Increased sales

If you’re wanting to ramp up your business to the next level, then it’s time to pick up that money left on the table. Without proper inventory forecasting, your business is losing money. According to a study done by IHL group, retailers lost $1.71 trillion due to out-of-stocks in just one year. This is easy money lost due to lack of forecasting. By preventing out-of-stocks you can prevent a big chunk of lost revenue, and cushion your annual revenue.
As you can see, implementing an inventory forecasting strategy is crucial in ensuring the success and future growth of your business.. Especially when you are in a transition and need to consider whether to hire more people or make that big inventory purchase, inventory forecasting is an essential tactic to lower risk and increase performance in your decision making. 2019 could be the year you save you hundreds of hours of mindless number crunching and even thousands in profit by simply implementing an inventory-forecasting plan.
[ictabs alias=”cta-1″]

Running out of stock is one of the last things that any retail business owner wants when a product is in hot demand. It is not only disappointing, but it leaves money on the table by letting your customers search for alternatives from your competitors. To avoid such a scenario, inventory forecasting needs to be utilized and implemented across all retail businesses, from mid-sized operations to large-scale enterprise companies.
Inventory forecasting isn’t simply a matter of analyzing past historical trends and predicting future demands. Accurate inventory forecasting requires the right data set from multiple data sources.
Before diving into the data and stats surrounding demand forecasting, it’s worth noting that, within the supply chain context in the eCommerce industry, there are three main types of forecasting, which are:
Demand forecasting:  This is the investigation of the companies demand for an item or SKU, to include current and projected demand by industry and product end use.
Supply forecasting: Is a collection of data about the current producers and suppliers, as well as technological and political trends that might affect supply.
Price forecasting: This is based on information gathered and analyzed about demand and supply. Provides a prediction of short- and long-term prices and the underlying reasons for those trends.


90% of Retailers Fail in Forecasting Since they Ignore Lost Sales

A recent study carried for 2018-2019 period by Neogrid points out an important aspect that many retailers ignore when making their forecasts. The report says that 90% of small businesses do not use their past lost sales to make future predictions. Most of them only focus on demands which sometimes changes hence resulting in huge losses.

With a report of past losses otherwise called historical lost sales, the prediction will most likely be reliable. If you, therefore, run a retail business and would like to make accurate predictions, then make sure you have figures of your historical losses. Use them together with stats on demand, and your inventory forecasting won’t fail.

Retail Businesses Face Serious Problems Even After Spending a Lot on Inventory Management

Reliable information from Bossa Nova, a leading provider of data service says that one of its surveys found that even despite the huge spending that retail businesses make, 73% of them still make inaccurate forecasts. It further reports that most of the problems encountered are as a result of price inaccuracy among others. It, therefore, means as a retail businesses owner, you need to take the time to get accurate prices if you want to make accurate inventory forecasts.

Automating Your Retail Operations Boosts Productivity and Accuracy

Bossa Nova survey report indicates automation could be all you need to improve your productivity. In fact, 73% of the retail businesses interviewed reported that their employee productivity improved when they introduced robots. Furthermore, the same study says that 74% of the retail business owners interviewed expressed their confidence in automation. They argue that their accuracy in inventory forecasts increased when they automated their operations. You should, thus, consider automating operations as well as predictions if you want to improve accuracy, and most importantly, the productivity of your employees.

67% of Retail Businesses Think that Inventory Analyses and Forecasting is a Waste of Time

While inventory analyses and forecasting is being promoted as one of the strategies of making reliable predictions about the future, some retail businesses see it as a waste of time. In fact, 67% of businesses interviewed in Bossa Nova survey released on 28th Feb 2019 feel that spending time analyzing inventory isn’t a good way to use employee’s time.
Instead of spending time on inventory forecasting, most retail businesses often focus on serving the customers present at a given time forgetting that the future is also important. While such an approach can help maximize profits, it is important to note that demand changes with time. A business can only rest assured of existence in the future if it plans ahead through inventory forecasting.

Most Retail Business Lag Behind Technologically

Over 80% of retail businesses lag behind when it comes to the use of technology to find solutions to problems. What is happening is that technology is rapidly changing, and there are so many new technologies that retail businesses can utilize these days. Are you among those lagging behind? Your retail business can make great strides with the right technologies.
In conclusion, it is crucial for retail businesses to plan for future sales, and how to meet the demands of their customers without running out of stock. Alternatively, having excess supply will also mean losses and failed planning.


Curve uses machine-learning based prediction technology, allowing companies to accurately forecast sales, products, and support requests, to increase revenue and optimize profitability. Our unique technology goes beyond traditional business intelligence, by recommending the right solutions based on use cases and customer segments.

According to a report published by eMarketer in 2016, the trade and commerce sector will experience double-digit growth until 2020. During this period sales are expected to increase by over $4 trillion.
It’s clear that only a handful of industries can boast about such a beaming future. To make sense of our rapidly changing industry, we’ve compiled for you some of the most disruptive and potentially beneficial trends in e-commerce that marketers and consumers can expect to see in the very near future.
Greater Integration of Machine Learning and AI
Given the increase in marketing and business automation, it is inevitable that the commercial sector will continue to be influenced by a deeper level of artificial intelligence and machine learning in the years ahead.
In fact, machine learning is already integrated into today’s leading e-commerce retailers. In the upcoming years, however, additional e-commerce retailers will increasingly utilize the many benefits that machine learning offers in order to maintain their competitive edge.

Additionally, product recommendations, upsells, product bundles, as well as inventory forecasts, are also poised to become even more accurate and helpful. As a move away from keyword and human-based recommendations occur, merchants with a wider range of signals for product purchases history will become evident. In essence, retailers will have the power to know what the customer wants, before the customer does.


Voice search
It’s becoming increasingly difficult to talk about retail search without mentioning the advent of voice search. In the near future voice will be one of the leading drivers of online sales innovation, specifically with consumers on the go.

With an increase in the adoption of smart home appliances such as amazons echo and Googles Home, retail purchases are witnessing the incorporation of voice search,
Voice search, particularly in the smart speaker market, is not just a matter for convenience and neatness anymore, but it is the next stage for customer loyalty. For instance, the sales completed via Amazon Echo units also provided retailers with many new selling opportunities, with upsell rates of more than 60% for some product lines.
Faster shipping and better delivery logistics
One of the very few remaining differentiators when it comes to e-commerce sectors is the time and quality of delivery logistics that a retailer carries out. As we all know, Amazon is the indisputable king of e-commerce delivery and seems to remain firm on its throne for the coming future. Even more intriguing is the data on Amazon’s fastest deliveries- just eight minutes for a forehead thermometer and a mere nine minutes for 5 pints of ice cream.
We’re not too far away from a time when we can expect Amazon and other e-commerce retailers to step up their logistics game and offer their customers lower delivery times and better services.
Unprecedented growth in mobile checkout systems and IoT
These days, without mentioning the use of mobile checkouts and payment systems, anticipated e-commerce trends would not be complete. Mobile payment has been one of the most brilliant changes to the way people shop since e-commerce has skyrocketed. The mobile payment market has increased steadily since 2015, and now there are ten different systems available today. These also include Apple pay and Google pay as well as proprietary offerings from different banks including Chase and Softbank.
With ongoing innovations and new technologies being introduced daily, the e-commerce sector has and will continue to witness one of the fastest evolutionary shifts that the industry has ever seen.

In the last decade, artificial intelligence has made huge advancements and has integrated into almost every field, especially businesses and marketing. One of the major uses of AI and machine learning is sales forecasting. With the ability to process so much information at an incredibly rapid pace, it has become extremely beneficial for companies to turn towards the AI rather than traditional sales forecasting simulations.


Most people get confused between artificial intelligence and machine learning, as they may carry out similar tasks, however, there’s a clear difference between these two technologies, and we’ll help break it down for you.
First, it’s safe to say that the terms “Artificial Intelligence” and “Machine Learning” are often used interchangeably because both describe the use of software and hardware that enable a machine to be “intelligent.” However, the difference is that “Artificial Intelligence” is a broader term for providing machines with the ability to perform rational tasks, while “Machine Learning” is a subset of AI that encompasses the use of data for the machine to learn.


In general, AI is a concept where it is possible for a machine to “think” or react like humans. AI, Neural Networks, can learn by examples to execute arbitrary tasks. For instance, an AI ‘CRM’ solution can learn to respond to emails like humans. In essence, they can generate by teaching examples and very complex rules that humans follow.
Some people believe that just by stacking deeper and deeper artificial neural network, we will get a self-aware AI, and they call that hypothetical event ‘The Singularity’. However, that is highly doubted by industry professionals.

Machine learning is a bit more specific, as its main purpose is to read and learn the statistics and algorithms and learn from the historical data. In a nutshell, Machine Learning is taught to recognize patterns and make decisions based on statistical information. 


While machine learning is taught to gather data and learn it AI is mainly focused on applying the data. AI’s main purpose is to increase the successes it has in any objective rather than machine learning, which aims to increases the accuracy. In essence, AI aims to stimulate natural intelligence in the computers however the goal for machine learning is to maximize the performance of the machine by learning new things from the data. 
Sales forecasting that uses machine learning techniques, however, draws data from all historical sales forecasts and creates a model that shows a typical path for a successful sale, from start to close, and then compares it to current performance. Anomalies and an off-track forecast can be quickly detected in the data, which gives sales leaders the opportunity to step in and redirect ecommerce sales.
Utilizing Machine Learning technology such as Curve helps your team make more accurate sales and inventory decisions. All of these enhanced activities improve overall sales effectiveness and drive growth in an organization. At Curve, our mission is to help sales teams improve your sales outlook and drive growth across the organization.