In the rapidly evolving world view, there is a need for new forecasting techniques that are resilient and flexible. The change is required more than ever before since, in the current times, an incorrect decision in any of the domains such as logistics, production, inventory, and retail, to name a few, can pose an existential question to any organization.

Challenges with conventional forecasting models

Any brand throughout its business journey makes decisions to its benefit based on the guiding principles of past data. It is well experienced, as the COVID-19 situation unfolded throughout the world, it not only affected normal life, but also changed the behaviour and psychology of humans. Some changes in consumer behavior like shift to online platforms are more permanent than changes like focused spending. These changes were so quick, that businesses which relied only on the past, saw great variance between forecasts and the actuals. In such scenarios, no concrete decisions can be made based on these models as it would have far reaching impact on the top line as well as bottom line of the brand. The common reasons for most of the forecasting models to fail are lack of indicators to factor in sudden events, heavy dependency on earlier sales patterns, confined seasonal patterns and so on. To redefine this conventional approach, it is necessary to account the variables linked with these changes to provide better insights into changing trends with a reasonable accuracy and lead time.

The change indicators

Leading and lagging indicators are types of technical indicators that either give an indication of what could happen next within the markets or provide information on what has already happened. Leading and lagging refers to whether the indicator moves before or after another metric, such as price action.

To identify the correct indicators for your business, asking the right set of questions is the key. Do financial, economic or un-conventional indicators emerge as potential business influencers?, Here are some common indicators and their influence area –

Financial Indicators indicate trends in the consumer buying capacity while economic Indicators indicate industrial production rate and how the market is constantly changing. Un-conventional indicators like google mobility index indicate people movement around recreational centers, shops, medical facilities etc. While economic indicators are no-brainers, they lack localization and are typically published after-the-fact whereas indicators like Google mobility are localized and available frequently. Hence considering a right mix of both ensures quick learning and implementation mechanism.

For many indicators, the relationship with sales is dynamic and evolving due to the wavering market conditions. Investigating the trends of these lagging and leading indicators brings out fascinating insights about their true nature and cause of the change in pattern.

What indicators should you consider?

Leading indicators may be able to follow the current market dynamics rapidly and provide foresight in business well in advance. Hence identifying and using the relevant leading Indicators for business forecasting in real-time can significantly improve the model’s predictive power and can provide crucial accuracy gains. These indicators should be well supported by business justifications and not based on spurious statistical correlation.

Real-life examples:

For example, Airline passengers can be an indicator of luxury product sales. As more people visit airports, more is the footfall for the hub of luxury brand stores, leading eventually to a higher demand for these products. There is a time gap between the booking of the airlines and the sales, and therefore, the airline passenger could be a useful leading indicator.

Another example would be lockdown index as an indicator of luxury product sales. As the lockdown index decreases, the number of people traveling increases, leading to higher demand for products at stores. Again, there is a time gap between lockdown index relaxation and travel plan execution, providing enough time for the companies to prepare for upcoming surge in demand.

Practical implementation of such a non-conventional model for a brand retailer, shows some fascinating correlations like increase in stock market’s S&P 500 performance in the past three weeks positively impacts its current sales while increase in lock down index in the past two weeks decreases the current sales. Similarly google mobility indicators like percentage change from baseline in movements amongst parks, grocery stores, and pharmacies also impacts sales.

To identify these leading indicators, one should study correlation pattern between sales and various time lags of these indicators. As this relationship rapidly changes with time, these observed indicators will constantly influence sales showcasing their highly predictive nature. Once the right indicators are identified, data availability could be the next challenge. Data availability challenges can be more often resolved using proper data mining, modelling and feature engineering techniques.

What are the trade-offs:

A trade-off between business guidance and correct statistical models can create desirable forecast with added confidence using model evaluation metrics like accuracy or mean absolute percentage error (MAPE). Creating a transparent framework can offer significant business insights for managerial adjustments to the forecasts and the eventual acceptance of the forecasts in the organization. Since the data required for this type of modelling needs to be recent and real time, the practical usefulness of this non-traditional forecasting framework is limited to shorter horizons. The framework has the potential to impact the business positively given traditional models may fail to cope with the situations arising in uncertain times like COVID pandemic. The accurate predictions will drive in-time decision making that may lead to better product availability and higher customer satisfaction.

To build a forecasting model that may impact your business positively, be observant and identify the events, triggers or things impacting for your business. Analyse your position in market and changing sales pattern within your consumer behaviour.

Infocepts specialises in solving a variety of data science problems using techniques like Predictive Analytics, Forecasting, Cluster Analysis, NLP, Recommendation Engines, Computer Vision and many more.

Get in touch to know more!

Recent Blogs

Analyzing data on products is time-consuming, unengaging, and inefficient. Retail store managers sit down at a desk and plan out the store without actually being able to see the store or products. They can see the analytics but the actual store layout, feel, and atmosphere is lost when they are distanced from it, making planning from an office and product placement that much more inefficient.

Infocepts collaborated with Neumont College of Computer Science to implement Power BI reporting and functionality with Microsoft’s HoloLens 2, allowing users to not only see data on products but also see the product in the HoloLens world.

HoloLens gives retailers easy access to data reports and models of their products while on the store floor, enhancing the relationship between the store managers, employees, and the products. Employees can view 3D models to help find products they aren’t familiar with and real-time data reports help managers make decisions on product placement and orientation all while being able to see the physical layout with holograms projected from the HoloLens 2.

With every industry and organization now going digital, an enterprise-wide automation approach is key for any organization to remain relevant and succeed in the new age markets. Most businesses fail to scale their automation initiatives due to a lack of clear Organization wide strategy and not being able to quickly evolve to the needed changes and the new ways of working.

To keep up with digital disruptions and competitors in the industry, it is important for businesses to implement a self-evolving intelligent automation strategy which helps constantly improve process efficiencies. Intelligent automation can help businesses achieve their automation goals by combining the power of AI, robotics and data-driven insights with a long-term vision which accounts for transforming people, processes and technologies.

Check out this on-demand webinar to understand:

  • What does Intelligent Automation mean?
  • How a global market research firm is leveraging Intelligent Automation in their Connect Platform?
  • The benefits and learnings from the Automation project
  • Infocepts advice on how to go about building automation capabilities in your company?
Back to Blogs

Data is the most important asset for any organization and is the key to its growth and success. Analytics, which is at the heart of any digital transformation initiative empowers new age organizations to leverage data effectively to make smart decisions.

Every organization today is trying to invest significantly in Analytics and it’s a core area of discussion in board meetings. But then, why do so many Analytics projects fail to make an impact? While there are many reasons for failures, here are the top six that you should be aware of before kicking off any analytics project.

  1. Lack of Management Vision & Support:

    Top management sets the tone for any organizational initiative and Analytics is no different. Visionary management team will support the need to build a data-driven culture within the organization.

    • Humans have the tendency to resist any change. If analytics programs are kicked off just to follow the market trend without setting up the business strategy, it’s bound to fail. Business leaders should include analytics as part their vision and handle the change management effectively through inclusivity and trust building measures.
    • Analytics projects are traditionally hard to implement. They typically start with a Proof of Concept(PoC). Bringing analytics projects from conceptualization to production requires clear understanding of business goals to everyone involved in the program. We have seen the crazy race to launch the Analytics programs and many of these projects go down due to lack of management vision and top-down support.
  2. Poor or Missing Data:

    Data driven originations have survived the most challenging of the conditions because they believed in their data and utilized it to the maximum for accomplishing their executive goals.

    • It is important to continuously check the quality of data and make necessary changes to the data cleansing routines as required. Make the Data quality routines flexible so that they can continuously adapt to new rules or sources of data.
    • Business processes are becoming more and more complex and end users are continuously looking for new product lines and real time assistance. Understanding the data required for any Analytics model is the key to success.
    • Idea is to bring right data by effectively understanding the business requirements and baselining the processes. Data should be able to power analytics engines effectively which can result in actionable insights with greater impact.
    • Good data will aid the success of any analytics project and on contrary bad choice or quality of data will make the task difficult and ultimately take down the complete analytics investment.
  3. Missing Analytics Governance:

    Most of the Analytics projects are built on small PoC/MVPs and once it’s successful, business/product owners demand to build more use cases on top of this without strengthening Analytics Governance processes.

    • Analytics governance should go hand in hand with the first ever Analytics project and should not be left aside for future enhancements.
    • Things like Security should be the day 0 priority and should not be ignored even when you are delivering a small PoC. Go for an effective role and access management so that the trust is not compromised at any level.
    • Analytics Governance ignorance can result in multiple points of failures such as security breaches or reduced performance which eventually may bring the bad name to the organization and complete analytics initiative may go for a toss.
  4. More Time to Market:

    It is a furious competition out there and if you are not able to deliver on time, someone else will.

    • We have seen cases where Analytics programs were delivered but it failed to catch up with the consumers as the competitor was ahead in the game.
    • Time to Market from ideation to finished analytics should be a short cycle and idea should be to deliver results quickly to the business through short MVPs.
    • From technology point of view use the power of cloud to eliminate infrastructure bottlenecks. This will not only shorten the complete cycle, but you will be able to come back to the drawing board quickly in case of any inadequacies. Adaptation is the key to success and the feedback loop should be kept open.
    • Create a lean Project management schedule even if it is a PoC. This not only helps in tracking activities closely, but any bottlenecks can also be managed immediately.
    • Have simple visualizations on top of your analytics output which can be easily understood by the business teams. Many of the times we have seen that end users who consume analytic results fail to interpret analytics output and ultimately the UAT cycle is stretched.
  5. Missing Appropriate Team members:

    While it is okay to have cross trained team members in your analytics team, at least have one strong resource who understands the technology and is curious about what that data might reveal to solve the business question that analytics is trying to answer and bring required Data Science & Machine Learning leadership.

    • Working on an Analytics project without business stakeholder’s active engagement can lead to a weak hypothesis and ultimately the Time to market is stretched.
    • Keep business stakeholders in your team as product owners from day 1 even for a small PoC. They can be owners of the business process that you are trying to simplify. Having them in your team can reduce the chance of failure as they can continuously provide the feedback to improve your model.
  6. Ignoring Regulatory compliance requirements:

    Businesses may have to pay heavily if regulatory compliance are missed.

    • While analytics for an organization is rewarding, it may become a high-risk issue if it is not organized and compliant to regulatory laws.
    • Most of the time Analytics projects are kicked off in a rush and delivered technically without considering the regulatory and compliance requirements for that region/business. For example, if you are working for a European client, GDPR is something which you cannot ignore else you will never be able to productionize your model even if it’s technically super.

Get in touch to know more!

Recent Blogs
Back to Blogs
Recent Blogs