The post Generative AI, a New Catalyst for D2C Expansion appeared first on 91����.

The post 10 Critical Learnings to Win in D2C in Mid to Large Sized Organizations appeared first on 91����.

It is a common situation that most shoppers face while buying packaged goods online. Due to high demand many daily used products go out of stock in retail sites. But it is more annoying to experience longer time in any shopping website due to lack of clarity about how to select and pay for a product. Direct-to-customer (D2C) is the new trend shaping the consumer-packaged goods (CPG) industry across the globe. Primary reason being low entry barrier, which is enabling private label brands to appear in the market with frequency higher than ever. However, not all brands could sustain the race of attracting consumers to their brands. It is more due to the marketing strategy they follow than the quality or features in the products. Drawing consumers to the products is the primary major challenge in this business model. Second major challenge is ensuring continuous availability of products, which means ensuring an uninterrupted supply chain process. If we introspect more into the primary challenge, we find three reasons underlying. First one is all about understanding the need of each & every customer and designing product as per their requirements. Second is keeping a tab of competitors’ offerings in the marketplace. Third is using information related to earlier two cases to develop personalised buying experience for every customer. The only solution that could help us resolve all these problems is data. Data is the ammunition in this expanding war of customer acquisition and retention. Collection of data about customers’ preferences and competitors’ new offers, storing those data and using those effectively are of primary importance in building a successful D2C business model.

If we go deeper into this, we find that next level of challenge is identification of data. It is customary for every marketer to understand and find the type of data one needs to understand customers’ requirements. Parallelly, one needs to find the data required on competitors’ offerings to strengthen the grip on the marketplace. Once understood, firms should think about the resources through which all these data can be collected and stored. And finally, how these data can be used to generate insights about customer’s behaviour.

To help firms in this journey, digital technology services are on the rise. The advent of intelligent automation has equipped the software service providers develop digital tools to understand the ongoing trend and find which areas need more focus to make the business run profitably. Robotic process automation (RPA), cloud technology, Artificial Intelligence (AI) based algorithms and machine learning (ML) programs are examples of digital tools which have paved the way for technology focused CPG firms to monitor their businesses closely and engage consumers more effectively. Every consumer has a different and unique way of shopping. Therefore, engaging with each consumer through the right channel, right promotion and right offer is undoubtedly a critical task. In top of that increasing penetration of mobile technology has brought all category of consumers at the same place and at the same time resulting in an extra level of complexity in data collection. Therefore, developing a robust data storage facility is no more a choice but a necessity for managing such increasing diversified consumer base. 91���� through its rich experience of working with multiple CPG consumers can provide both on-premises and cloud-based database solutions to manage terabytes of data on a continuous basis.

Once the data storage facility is set up, suitable data collection resources should be developed to ensure uninterrupted data feeding to the repository. Whenever a consumer engages in any purchasing activity through online channel, millions of data are transferred to the marketing firm. Multiplying this with number of available channels, nearly trillions of data are needed to be handled every day. Hence, the solution is to have resources having the capability to find relevant data in any format from any channel and incessant feeding of these data to the storage facility. 91����’s intelligent automation team can develop any customised intelligent bots using robotic process automation (RPA) for collecting data from any channel at any time with 100% efficiency. Not only from websites, but these bots can also even identify the necessary data from any document in any format. This can help the firms analyse multiple purchasing invoices to figure out average purchase value for any customer.

After collection the data, next important steps are identification of relevant KPIs and development of analytical models for the purpose of understanding the status of ongoing business and generation of insights about customer’s buying pattern. 91���� has a dedicated analytics team who has developed analytical models as per business need and has helped firms understand consumer journey at every touchpoint starting from exploration to procurement of any product.

After data management the next critical area where D2C firms should put highest focus is managing the supply chain of entire processes. If designing products as per consumer’s need is the primary challenge that D2C firms face now-a-days, then the next big challenge is taking these products to the consumer’s doorstep. The solution that addresses this concern is smart supply chain. Although most of the firms engage third parties for delivery of products, making the products available to delivery partner’s warehouses or distribution centres need a thorough monitoring of supply chain. 91����’s Industry 4.0 and Digital team together provide efficient and effective supply chain solutions with the help of Internet of Things (IoT), RPA and AIML. Not only our solutions ensure automated monitoring of entire supply chain process but also can eliminate the redundant processes, reduce the energy consumption at intermediate stages wherever possible and build models for optimising selection of packaging materials.

The problem that Sanaya faced at the beginning of this article could have easily been avoided had the brand manufacturer focussed on these issues and collected data about Sanaya’s buying pattern. Also, they should have ensured availability of the product at retailer’s site by adopting smart supply chain practices. Emerging digital technologies like robotics, artificial intelligence, cloud technology and IoT are a blessing for firms. However, leveraging these technologies to maximise the profit and capture the market share needs a blend of expertise & experience over the years. 91����’s rich experience of working with global CPG manufacturers in multiple channels and multiple regions for diversified products have helped develop suitable digital technology-based offers for D2C firms. In an industry like CPG where competition has been a paramount concern from new product perspective, emergence of D2C practice has made the situation more complex. To compete successfully and lead in the marketplace, firms must embrace the digital tools for navigating through the wave of unlimited new products.

Author:

Debal Chakraborty,
Principal Consultant

The post Brands that Embrace Digital will Stay Ahead in the D2C Model appeared first on 91����.

Imagine you are buying a few bags of potato chips to snack on. One bag has fewer chips than expected; the chips do not match the weight mentioned on the package. You will be disappointed. You will either complain to the manufacturer or simply stop trusting the brand. Worse, you could take to social media to express your anger, affecting the broader reputation of the brand. If there are a few extra chips in the bag, you will not mind it. But those extra chips can quickly add up to massive losses for the manufacturer. Either way, not controlling the grammage of products leads to unwelcome outcomes. This is not a new problem for the F&B industry. But new solutions are now available to contain and practically eliminate-the problem.

Variances in packaged food products is expected. The manufacturer of a 78 g bag of potato chips can perhaps tolerate a variance of +/- 2 grams. But by identifying the actual variance and tracking trends, upstream and downstream systems can be improved, costs can be lowered, compliance norms can be met, waste reduced and customers kept happy by offering a more consistent product. However, usually individual checkweigher or multi head weighers and baggers are used at the packaging stage to accept/reject products for the market—when it can be too late. To overcome this, the science of Extra Grammage (EGA) Optimization needs to be mastered.

The weight of packaged food products is a tricky affair. Something as simple as extra moisture in the chips or extra oil can increase the weight. The thickness of input materials (for example, potato slices, masala or salt deposition etc. ) or even the temperature of the cooking oil or frying time can cause higher or lower weights, or the vibratory nature of the manufacturing equipment can lead to variances.������

Often the selling price of a product cannot be changed. In such cases the manufacturer must resort to controlling the weight.

EGA optimization is a latest Industry 4.0 solution integrates all weigher “Machine Data” & “Process Parameters” and where continuously monitors the trend of Underweight & Overweight Rejections and Extra Give Away of Materials.�� Then Auto-Insights are generated basis factual data at frequent intervals, minute level & KPIs are measured EGA%, rejections% etc. and any deviations beyond acceptable limits are alerted to respective operators to fix the production parameters causing the variance immediately, minimizing the volume of rejected products at the end of the line. The solution works for both linear and vertical manufacturing and packaging processes.��

Vertical manufacturing and packaging processes need to be dealt with a little differently from linear processes (example: potato chips versus cookies). In a vertical process, the product drop happens to multiple buckets during production. The weight may vary because of product breakage or due to residual recipe material, accumulated in the assembly line, sticking to the product.

In current practice, many CPG companies have not integrated their Machine data. Right set of Analytics not used to create meaningful alerts for operators and to improve output quality. Our implementation of this solution in a large food production plant has shown significant results, that even a 1% impact is saving thousands of dollars. But this is what production plant managers will like to hear the most: ROI in our implementation was less than six months. This is a high-impact, quick-return intervention that every manufacturer must consider.

Author:

Siddaraju G,
Senior Principal Consultant,
Business Consulting Group,
91����

The post A “must-have” packing weight variation control technique appeared first on 91����.

Marketing and Trade Planning Needs to be Real-time and Data-Driven

By the time the organization works with distributors to collect data and plan a marketing and trade promotions campaign, markets have changed. The organization then puts its plans on hold while it comes up with better options. There is a need for systems that allow planning to be dynamic and execution to be fluid. 91����’s Intelligent Planning Platform for CPG organizations fills the gap. It enables high-impact near real-time data-driven planning that is focused, relevant, detailed, fluid and keeps the entire organization in synch with campaign goals.

Empower CPG Marketing Leaders with Intelligent Planning Platform��

The Intelligent Planning Platform serves as a digital nervous system to support marketing plans and execution. It tells marketing executive what to do, when to do it and why to do it. It can preempt markets by providing real-time visibility into what is happening in sales, marketing, trade promotion, schedules, volumes and the strategy of competition. Basically, it tracks and analyzes every parameter key to CPG CXOs.

It’s a Connected Platform:��

The system harmonizes processes across different parts of the organization that work together to deliver success. It keeps master data available to everyone such as distribution, marketing, communication, purchase, and finance, playing a pivotal role in converting information into plans. Its real-time dashboards assist in precise decision-making at velocity.

Enables Real-time Communication with Stakeholders

Success in fast-moving—and fast-changing campaigns—depends on the efficiency with which communication is maintained in real time with internal and external stakeholders, distributors and customers. The platform keeps the entire marketing ecosystem in synch.

Dynamic Planning, Execution and Decision Making

It is important to have plans defined and based on data. But it is equally important to have a system that can respond to change and manage quick course corrections. Our Intelligent Planning Platform allows teams to change decisions around everything, from volumes to SKUs and pricing. The system then provides the means to re-optimize the plan and follow through on the execution.

The world of CPG has been transformed over the last few years. Today, it has multiple ways to connect directly with the customer, collect an increasing amount of data and analyze it in real time. It now needs a system that can act flawlessly on the market signals. Our Intelligent Planning Platform is precisely that system. It supports high value planning and decision-making. It prompts and manages quick adjustments in execution. And it ensures that marketing dollars deliver target ROI.

91���� has implemented intelligent planning platform for Leading CPG Business. We implemented an Integrated Trade Marketing & Distribution Planning to Accelerated Speed to Market. To know more about our Intelligent Planning capabilities for CPG industry read our whitepaper “Intelligent Planning – The winning tool for CPG Business in the Digital Era”

Author:

Debjit Banerjee
VP, Business Consulting,
91����

The post Using an Intelligent Planning Platform to guarantee marketing success appeared first on 91����.

Vision-based computing or computer vision, aka machine vision, has grown tremendously in the last few years. The key reasons for the growth lie in the availability of affordable hardware, the growth in data sets and maturity in the science of Artificial Intelligence (AI) and Machine Learning (ML). With the COVID-19 pandemic accelerating digital adoption, vision-based analytics is bound to find wide-spread applications in several industries including manufacturing. The extraordinary drive for work place safety, the need for automation to improve productivity, and access to better quality will be the key drivers for the growth in vision-based computing. One indicator of its bullish future is reflected in a that found AI in computer vision market size would reach $144.46B by 2028 from $7.04B in 2020 (a CAGR of 45.64% from 2021 to 2028). Manufacturers who do not study use cases for vision-based computing in their organizations could lose out on the promise of generating business value and creating competitive differentiation.

An area where vision-based technology can be applied with great success is quality inspection. Take the case of manufacturing cookies in the food and beverage industry. Operators are deployed on production lines to check the quality of the output. They must examine each cookie for conformance to color, texture, shape, size, nut coverage and several other factors and benchmarks. These are important in an industry where consumers assess products visually. Human bias – even human fatigue or distraction — can affect the inspection process. Options such as interval sampling of products in a lab can improve the process but they too leave the gates open to flawed products reaching the market.

The solution is in using AI and ML-based algorithms to examine each cookie. Cameras scan the live production line before packaging, accurately picking out cookies that do not meet the pass range for quality. Even when samples are examined in an off-line mode in a lab, vision-based computing removes subjective biases.

Once a cookie on a production line is identified for non-conformance, a simple drop mechanism removes the cookie from reaching the packaging process.

Vision-based computing has several applications in factory environments. Most manufacturing plants already have several CCTV cameras used to monitor activity, human safety and business security. The number of cameras on a production floor can number anywhere between 30 and 100 – a number impossible for humans to continuously scan for aberrations. This is why these cameras are usually used after the fact, to investigate incidents.

However, the camera feeds can be analyzed in real time based on EHS guidelines and even used for automated risk audits. This means the investment already made in video monitoring can go the extra mile by identifying hazards in different work areas such as slippery floors, accumulation of materials, obstacles in pathways, missing or inadvertent obstructions around firefighting equipment, violation of safety norms by employees (such as not wearing hard hats or fall arrestors), unauthorized entry of personnel in restricted areas, and the entry and exit of vehicles in plants, warehouses, collection points and so on.

Not only can vision-based computing prevent issues or generate real-time alerts, but the data can also improve processes. For example, supervisors can immediately know how many vehicles are parked in a certain area, what type of vehicles are parked and for how long, the time taken to offload material from any vehicle—each data point allowing the supervisor to take quick and accurate decisions.

Vision-based computing is here to stay. And the race to adopt it has just begun.

Author:

Siddaraju G,
Senior Principal Consultant,
Business Consulting Group,
91����

The post Enhancing product quality and plant safety with vision-based computing appeared first on 91����.

It is never easy to stay on top of the factors that determine product development. These factors range from gathering information on what customers used in the past, their levels of satisfaction with existing products, how they can be persuaded to change their minds with a change in packaging or display, the impact of word-of-mouth on decision-making, competitive action, regulatory requirements, the intellectual property landscape, patents, available technology and ingredients, recipe suppliers…the list is long and daunting. This is where digital platforms come into play, supporting the effort to capture knowledge and let it flow into new product development.

There is an additional level of complexity involved. CPG organizations need to address a variety of time frames to get new products before consumers. Reactive changes to existing products may be required in the short-term. Some changes, such as shifting to sustainable ingredients, may be required in the mid-term. And launching a fundamentally new product, replacing existing products, may be required in the long-term. Also, long term sustainability and growth of the business would require the CPG organization to move quickly, focusing on product IP creation and raising barriers to entry. The question hounding every CEO pursuing new product development is, “Am I executing innovation and NPD process using the correct systems and methodologies, so that I can have the right products available just when required, to be used as the winning ammunition on the battlefield of the market?”��

To answer that question with confidence, the CEO needs to have a digital platform that takes products from concept to launch. 91����’s PLM based Digital Platform fills the gap. The platform is enabled with stage-gate driven accelerators and templates. It integrates business functions in the organization such as engineering, testing, packaging, graphics, commercial, marketing and legal, and enables them to collaboratively contribute to the innovation process at various stages. The platform, through its interactive dashboard, provides visibility into portfolio, programs and projects, captures who is working on what activity of which project, and the stage at which each project is. What the digital platform delivers is a system of urgency, flagging delays, identifying bottlenecks, sensing what is happening in the market and bringing it to the notice of the organization, and enforcing collaboration.

The need for such a platform has been felt for long. But the urgency has grown in recent years as end-customers are going digital. They now have the tools to look for customized, personalized and improved products. In response, CPG organizations need to work faster, conceptualize products overnight, come up with prototypes, test them and get them into the market before competition does. The only way to do this effectively is with a PLM based digital platform, such as the one provided by 91����, specifically designed to manage new product development and innovation.

Author:

Debjit Banerjee
VP, Business Consulting,
91����

The post Faster, higher, stronger: How digital platforms can win the race for new products innovation appeared first on 91����.

Traditional CPG manufacturers always lacked access to consumer data and insights and relied on retailers and ecommerce companies to engage with consumer. However, they are now realizing the value from consumer intelligence and are investing resources to help bridge the age-old gap with their consumers through targeted and personalized communication and services. Some are even transforming their Route-to-Market models to include more online D2C channels. The need to have a direct connect with the consumer has been reinforced by the current coronavirus pandemic scenario, where manufacturers are overnight initiating D2C channels such as stationing a sales van at a large apartment complex or signing up with a pizza delivery restaurant to deliver groceries.

But the fact that offline sales through brick & mortar channels still amounts to 89% of overall sales offtake, according to IRI E-Market Insights, CPG manufacturers focus on ensuring continued incremental growth through this channel. And empowering the sales rep becomes crucial to it.

Most technology advancements made by CPG manufacturers to serve their retail customers better, has been around SFA applications – largely focused on improving the productivity of the Sales Rep. This in-turn fosters a transactional relationship between the Sales Rep and his outlet. However, progressive businesses are looking beyond productivity objectives, obsessed on how to make their field sales reps more effective at the point of sales – moving from transactional interaction with retailers to a more informed and commercially focused conversation.

Unlocking the Data Gold Mine to Improve Outlet level Sales

In order to win at retail execution, CPG companies need to harness data beyond the usual – Sell-In, Sell-Out, Product Availability, Pricing & Promotions. For example, tobacco companies can benefit knowing which outlets are close to a sold-out concert venue. This hyper-local demand information known a week in advance can be used by the sales rep to recommend the outlets to stock up to meet the demand due to predicted increased footfall in that area. Similarly, it would be beneficial to understand the economic environment around an outlet – is it a residential or commercial area?; is it close to a rail station/ metro / bus stop?; is it close to a movie hall or tourist spot? They all provide footfall predictions and used for assortment decisions.

In the on-going quarantine scenario, it would be important to understand consumer’s current definition of essentials and accordingly plan for demand and outlet assortments. The US retail market has displayed clear purchase trends in this regard – when first the news of the pandemic broke out, shoppers hoarded toilet paper and cleaning essentials, as they slowly settled into their quarantined lives, there rose a strong desire to bake, uplifting sales of flour, baking powder, yeast and other baking essentials. Now as consumers are quite habituated to the lockdown, the focus has shifted to personal care, increasing sales of grooming products.

While social listening data and offtake data would indicate consumer purchase trends, integrating news and government health statistics are especially imperative, as they will provide insights on which areas are worse affected by health concerns, and how that will then determine the impact on demand in that area.

Data Sources – Internal and External

Outlet 360 will empower the CPG companies to ensure the right product in the right store at the right time and at the right price. It will use base attributes, transactional attributes, 3^rd��party attributes and derived attributes to generate personalized outlet level predictive insights on outlet value, assortment mix, order quantity, reach, churn, new product uptake, payment default, credit line and promotions.

Outlet 360° – Platform of Intelligence

Enabling Outlet 360° View and Point-Of-Action Analytics

To help our CPG client accelerate growth using intelligence, we have been building platforms of intelligence for them. These platforms are focused on delivering personalized experience, monetizing loyalty programs and new channels of engagement and commerce. We have been working on and end-to-end Customer Intelligence Platforms which leverages customer, business, demographic and social data to deliver adaptive experience to customer. One of the focus areas of this platform is an outlet intelligence hub that provides a single 360° view of the outlet. This is the foundation that empowers sales reps with “Point-Of-Action” insights to have a more meaningful commercial discussion during their outlet visits. This can also be leveraged to acquire indirect customers through personalized campaigns.

Customer Intelligence Platform – CPG

The platform assesses the value potential for an outlet basis its historical sales performance, peer group and catchment area analysis. This serves as a foundation for the sales pitch the rep makes to the outlet. Which products need listing? What business benefit will they bring in? How many other similar outlets in the neighborhood are selling these products? The platform’s insights can also personalize trade promotions targeted towards the outlet. What is the price range attractive for the outlet owner? What form of incentives will entice the outlet owner to make a bigger purchase? Would he like a credit limit extension or just a x% discount.

The insights can also help determine which outlet is a suitable candidate for a new product launch. Which outlets are on the verge of churn? What should be the order quantity taking into consideration their past out-of-stock statistics as well as any demand triggers in the outlet’s neighborhood.

Stay tuned as we show you how the Outlet 360° view enables sales rep transformation, making them effective at the point of sales – moving from transactional interaction with retailers to a more informed and commercially focused discussion. We will also explore some specific ‘Point of Action’ use cases, that demonstrate the data-driven conversation crafted for the sales rep by this powerful platform.

Author:
Bisakha Praharaj
Principal Consultant – Data

The post Platforms of Intelligence: Outlet Personalization appeared first on 91����.

Consumer behavior is seeing a dramatic shift in uncertain times

According to recent consumer surveys conducted by��Numerator��in US, 90% of respondents said that they have experienced a change in their shopping behavior due to the pandemic and 32% of respondents continue to stockpile goods that they usually don’t.��As the stockpiling continues, out-of-stock has emerged as one of the most serious issues, with 65% consumers experiencing a shortage of products. News reports and social media posts showing empty shelves have exacerbated the issue, and CPG manufacturers and retailers are challenged in keeping up with demand, especially as the effects of the coronavirus become more wide-reaching.

Shopper behavior has changed, and they have moved to online shopping to avoid contact.����There is a growth in online grocery shopping, with 11% of online shoppers making their first purchase in last 6 months and an additional 6% making their first purchase ever. However, the sentiments towards continuing online shopping post the pandemic remains mixed with many customers planning to return to stores for grocery shopping. Survey respondents expect a 3 to 8% increase in store visits post Covid-19 for grocery shopping, but a 7 to 9% decrease for non-grocery products.

McKinsey global consumer survey report an expected increase of 15 to 30% in expenditure on groceries and up to 15% on household products during the pandemic. While many welcome the increased demand, however, meeting the consumer demand has its own set of challenges. Manufacturers need to assess how to best mitigate the risks of supply chain disruptions and capacity limitations.

CPG supply chain is stretched thin

The sudden & dramatic shifts in consumer behavior and buying patterns has impacted the CPG supply chain and its stretched thin due to:

• Slowdown in production due to gathering restrictions and slower movement of goods
• Conventional just-in-time inventory & replenishment not able to handle the disruption.
• Shortage of raw material
• Unplanned shutdown of plants for sanitization following infection among workers and
• Increased worker absenteeism

Understand the dynamic consumption patterns using internal and external data

The rapidly changing market has increased difficulty for sales and operational planning. The changing product preferences, new consumption patterns and shift in demand channels, handicap the existing inventory planning and demand and sales forecasting models during the pandemic as well as during the post-pandemic recovery period. Hence, to capture the new trend in consumption during and post forced lockdown state, we need to look at potential sources of data for capturing the dynamic consumption pattern. Following are few potential sources of data which could provide information on dynamic consumption pattern during this situation:

• POS Data:��Point of Sales data for a few of the Key Accounts/Online Vendors with respective market share will help in deducing the new behaviour of these accounts.
• Weather:��Consumer-based businesses should be paying greater attention to the weather as about 5% of their total annual revenue directly impacted by the weather, with much higher sales variability in seasonal categories. Based on research by the American Meteorological Society, current U.S. economic output varies by up to $630 billion a year (about 3.4% of 2016 gross domestic product) due to weather variability.
• Consumer Sentiment:��Information like Consumer Confidence, Consumer Credit, Consumer Spending, Disposable personal income, Households debt to GDP and Consumer Savings can contribute a lot to understanding the consumer situation.
• Macro-Economic Data: Information like��Consumer Price Index (CPI), Producer Price Index (PPI),����Economic Activity Index, Unemployment Rate, GDP��from various sectors,��GDP Growth Rate,��GNP,��Labour data��and��Housing Index��will provide information on the economic situation of the region.
• Disease spread / mortality rate: Information on the number of��Coronavirus Cases,��Deaths��and��Recovered��will be a strong influencer on how the customers will react to this outbreak. For example, in case of a sudden large spike of the COVID-19, customers might be motivated to stockpile items.

Develop a short-term demand forecasting model using ML

Due to COVID-19 pandemic, the true consumption pattern might have shifted as compared to historical consumption pattern by Categories, Sub-Categories and Region. Even there could be lot of variations across different types of Stores as well – Large, Medium, Short Format stores. So, it makes little sense to observe past historical data for a long duration. Hence using the mentioned data sources, we would develop a short – term��Demand Forecasting��model to generate potential demands of different Category/Sub-Category/SKU level at daily level by��Geo-Spatial dimensions��and��Store Type��using sophisticated��Statistical/Machine Learning algorithms��that would provide significant confidence level of forecast accuracy. This would enable the��Trade distribution, Supply Chain and Manufacturing��functions to take right steps and measures to cater to those future demands with high degree of confidence by reacting to those demand signals.

The core component of the model might be a traditional forecasting models like;

1. Multiple Linear Regression model with ARMA errors,
2. Box-Jenkins ARIMAX (Auto-Regressive Integrated Moving Average with suitably estimated parameters from the data)
3. More sophisticated algorithm like��Dynamic Linear/Non-Linear Models – Gaussian State Space Models with Kalman filters which essentially includes models like UCM – Unobserved component Model, Bayesian Structured Time Series Model, Prophet
4. Highly computationally intensive models from the class of��Deep Learning Models like LSTM��using daily historical POS data in the presence of other data sources as mentioned earlier along with the data representing consumer behavior.

All these models are capable enough in producing accurate forecasts with reliably high degree of confidence when applied to short term time series data, provided enough variation in trend and seasonality exits in the data. Final model for production usage would be decided based on the��accuracy metrics��and��model robustness.

Consider a small historical window for forecasting models

The��main difference��between the traditional models used so far in the industry are quite prominent. While standard forecasting models consider a sufficient historical timeframe to capture the long-term trend, we will consider a small historical window, say last 3 months. This is because due to COVID-19, the trend and pattern of total sales would have shifted dramatically. Hence it makes little sense to observe past historical data for a long duration. Also, an in-depth region-specific analysis of the causal relationship between COVID-19 needs to be carried out. It is to be remembered that the overall COVID-19 trend of a country is not enough to capture the local trend. For places which have a high spread of COVID-19, the��average value per transaction (ATV)��will be high due to bulk shopping, but the��visit count��will be low, as customers will be reluctant to leave their homes. Whereas for areas where COVID-19 spread is low, the buying pattern might be more regular. So, the causal relationship analysis must be more granular. For each of these regions, a separate model needs to be created after accommodating the influence of COVID-19.

So, in conclusion the Short-Term Demand Forecasting model should primarily composed of 3 parts:

1. Downstream Data Integration:��Analyzing point-of-sale data from different regions, markets, brands and distribution channels to better understand consumer behavior.
2. Measuring the Impact of��Demand��Shaping Actions (DSA):��Recording and determining the impact of so-called demand shaping events like COVID19 in this case.
3. Latency Reduction (LR): Model demand more frequently — weekly, or even daily

Our short – term��Demand Forecasting��model is more practical in the sense that it is more attuned to the current scenario and changing dynamics incorporating rational downstream data integrations, capturing demand shaping events Through frequent model recalibration including newer data, the model would deliver superior performance in forecasting future demand.

Do get in touch with our Data Science team and CPG SMEs who has decades of experience in building CPG domain-specific analytical models. We have been helping world’s largest CPG companies with their customer insights, supply chain planning, sales/trade and distribution planning and operations. We can help you thrive and revive your business in this new normal.

Author:
Sumit Mukherjee
Sumit is a Principal Data Scientist

Anindya Neogi
Anindya is GM, Chief Data Scientist at 91����

Reference:

The post Predict Consumer Demand in COVID 19 with a Short-Term Demand Forecasting Model Using ML appeared first on 91����.