For any new product launch, the initial few months are a little unpredictable. Driven by large investments in campaigns and promotions, the product can have really elevated values of the month-over-month sales growth. Another reason why the number looks big is that the previous month’s sale (which forms the denominator while calculating sales growth) is small in the initial months.

It takes a while for the product to stabilize in the market, and finally reach a state, which we can call the steady-state. In this steady-state, the product stops having large and abrupt changes in sales (monthly, weekly or daily)…


When a consumer goods company sells products to retailers, it’s very useful to determine the sales potential of each product in each retailer. They could use these potentials for a range of applications, such as recommending customized assortment, launching targeted promotions, improving visit schedules of the sales representatives, and so on. Now, there are a number of ways to solve this problem through statistics and machine learning. One of the most common methods is training a model (for each product separately) by creating a dataset of retailers and their features as shown in Fig 1 and setting the product sales…


Consumer goods companies typically indulge in B2B business. For them, retail stores are not only their customers but also facilitators who connect them with the end consumers. Hence, companies have the incentive to push more and more types of SKUs to these retailers, so that they can adhere to the requirements of more and more consumers. However, there are upper limits to this. Any additional SKU requires negotiations and discussions with the retailer. They have no reason to believe why the new SKU, which they have never bought, is good for their business. …

Source —


When it comes to searching for a job, salary is always a huge factor anyone takes into consideration while choosing a company, profile, and location. Everyone has attended talks and read articles that reiterate that other factors like good work-life balance, nice colleagues, interesting projects, and so on are equally or even more important. But nevertheless, let’s face it, salary remains a top consideration for most people.

Now, a job’s offered salary is influenced by only one factor — the gap between demand and supply of the skills and qualifications required. …


Recommendation engines have been a heavily researched topic for years. An extensive literature review shows that a lot of approaches can be used to arrive at top N recommendations. From user-user similarity (demographic filtering, collaborative filtering) to find similar customers, to item-item similarity (content-based, text-based, ratings-based) to find items similar to a customer’s favorite items, each approach ranks top products on a different scale, using a different metric.

Now, each algorithm has its own evaluation KPI, which is typically based on what it tries to estimate/optimize. But what if we want to compare the results of very different approaches like…


Most businesses have seasonal trends in sales. Often there are certain months that show a spike as compared to the rest of the year. But where this spike occurs varies a lot by industry and even products within the industry. Let’s talk about the Indian fashion industry. Most shops witness multiple spikes throughout the year, especially during the festive seasons. But for a particular shop, the type of outfits that see a spike during Diwali will be different from the ones that see a spike during Eid. Although the total sales might look very similar, the products that contribute to…

Ayush Garg

I am a data scientist by chance, not by choice. But I have simply fallen in love with this field.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store