Aug 5, 2020

Measurement During a Pandemic with Analytic Partners. An Interview with Analytic Partners’ Konstantinos Spetsaris

Measurement at any time is filled with challenges. There are so many different datasets and parameters to use to quantify an increasingly complex consumer journey.
Now, during a pandemic where the entire landscape is shifting, the task becomes even more complicated. Konstantinos Spetsaris, SVP, Analytic Partners believes that we can apply specific methodology at this time to make greater sense for future forecasting. His company, he explained, offers, “adaptive solutions (that) integrate proprietary technology powered by the latest data science delivered through our platform and high-touch consulting.”

Charlene Weisler: What goes into accurate measurement of and during a pandemic?

Konstantinos Spetsaris: With so many forces at play, a holistic econometric model is best suited to accurately measure and decompose the impact of Covid-19 and its compounding impact on other business drivers such as media, operations and direct to consumer marketing. A simplified formulation of an econometric response model where all controllable and non-controllable drivers are in included as predictors (independent variables) would look like Response=f(Marketing, Non-Marketing and Macro Factors). The model lends itself to quantification and decomposition of impacts, reporting of core performance metrics (ROI, cost per acquisition, response/unit of support etc.) and scenario planning (simulation and optimization).

Weisler: How can you maintain quality data and feedback?

Spetsaris: We are expert at auditing, cleansing and validating data elements to be analyzed.  Our ROI Genome, an integrated database of benchmarking metrics, enables us to sense-check data inputs, which is complemented by a series of algorithmic validations, business logic, and human checks. Our data audits score all model inputs for both aggregate (accuracy, consistency, granularity, completeness) and user level data (coverage, quality, detail, integration).  We work with our clients to identify and resolve data gaps by supplementing (i.e. augmenting the partner ecosystem) or by creating proxies for missing data.

Weisler: Does measurement vary by industry, consumer category etc? If so how?

Spetsaris: Measurement varies in the sense of which KPIs are most critical to any given brand within any given vertical, as well as what data is available per industry. For example, there are industries with an immense amount of 1st party data, like financial services, which allows for extreme deep dives. Conversely, in industries like CPG there is a lack of 1st party data, which calls for a different process to draw out insights. 

Based on the industry, type of data available and KPIs, we can align candidate data inputs to be tested empirically in the model. Our fully specified model includes marketing, non-marketing and known external factors, but given the atypical and disruptive nature of Covid-19, we further explore other indicators which may have a significant impact on sales. These factors may provide additional insights into how changes in consumer behavior: e.g. reduced mobility, increased online shopping impact business performance. Inputs are rigorously tested on significance, independence (multicollinearity), in and out of sample fit (for predictive strength) and data source sustainability.

Weisler: What data is most important?

Spetsaris: What data is most important really depends on what business question is being asked. For that reason, it is critical to have a holistic measurement system in place that allows available data to be viewed through different lenses and dimensions, in order to extract the most relevant answer.

A few examples of the most important factors to consider during the Covid-19 crisis may include:       
> Bayesian Causal Impact – measures a signal in sales itself and the difference beyond expected response variable (synthetic baseline)
> Human Mobility data to account for restricted movement based on government stay-at-home orders
> Macroeconomic Indicators such as consumer sentiment, consumer confidence etc.
> Financial Indicators such as the VIX (Volatility Index) for financial services firms
> Store Closings and Operational Changes in Services e.g. no longer offering dining in for restaurants or adding a service e.g. curbside pick-up, changes in business model B2B to B2C etc.
> Category Base Sales to capture shifts in consumer demand towards certain product classes e.g. disinfectants, cleaners, shelf stable food
> Scaled Indicator Variables to capture Out of Stocks and the impact of stockpiling as a result of the initial panic mode buying at the onset of the pandemic
> Covid-19 Incidence as a leading indicator to government orders to shelter in place etc.
> Google Query Volume for specific search terms such as “lockdown”, “virus” etc.

Weisler: How can we effectively capture the impact of Covid-19 with so many other forces at play?

Spetsaris: We recommend starting with a holistic measurement framework such as Commercial Mix Modeling that incorporates controllable, non-controllable, and macro-factors in order to isolate the impact of Covid-19 on the business. From a measurement perspective, there are several factors to consider including: time horizon (immediate vs. longer term impact), industry (benefiting or negatively influenced and to what extent) and unique brand / business dynamics (% of sales impacted, geographic footprint, etc.). As an initial analytical objective, we recommend beginning with descriptive data analysis to help define the impact window in terms of business units, sales channels, consumer segments, and time. The goal is to identify where the impact of Covid-19 may be manifested in the dependent variable and gauge the order of magnitude vs. expectation. This helps refine our search for the right data inputs for Covid-19 as businesses are impacted differently.

Weisler: Can we still leverage historical results to predict outcomes given this unprecedented, non-regular event?

Spetsaris: In a word, yes. Covid-19 has disrupted every business in some capacity, which has influenced business and marketing plans and forecasted performance. In this chaotic state, data and analytics become even more important and measurement approaches must adapt. It is critical to update existing models to reflect new consumer behavior and continuously refresh to assess how these changes impact business performance. But, without an accurate understanding of historical insights and principle based learning as a foundation for these updates, there is no way to measure progress or success – nor is there a way to understand when and if consumer behavior and other key factors have returned to “normal.” 

Weisler: How will we know the lagging impact of Covid-19 as we shift to stabilization / recovery and revitalization phases?

Spetsaris: In the current environment, it is not enough to just know how much a business has been impacted by Covid-19. Brands need to know how the underlying consumer behavior has changed, and how it may continue to change, and better understand the pandemic’s impact on marketing and media channels, shopping habits, competitive actions, and overall business performance. Given the disruptive nature of Covid-19 its epidemic and economic consequences, decisions taken in the short term will have significant ripple effects down the road. With a robust and holistic model framework in place that incorporates all business drivers including the economic and Covid-19 impacts detailed above, brands will have a foundation to monitor business performance on an ongoing basis as we shift into stabilization, recovery and revitalization phases.

This article first appeared in www.Mediapost.com

No comments:

Post a Comment