The Need to Infuse Collaborative Innovation Into the COVID-19 Era

The Need to Infuse Collaborative Innovation Into the COVID-19 Era

By Nishrin Kachwala, Harshita Chopra, and Tanya Dixit


How diverse global technology teams can positively influence the future through new modes of innovation.

The COVID-19 pandemic has given us an imperative reminder of the existing gap among global communities. The digital divide and deep-rooted inequality have been affecting vulnerable populations around the world. As a result, countries are facing high uncertainty with far-reaching consequences on education, healthcare, and unemployment rates.



Wordcloud (created from the blog post text)


“The lockdown created fear and panic; The country is already in disaster. People cannot get to work or their business meaning they can no longer earn a living. The casual workers who survive on a daily wage also suffer. The government has promised food donations for vulnerable people who have lost their source of livelihood but have yet to fulfill. The cause has led to an increase in thievery and other sorts of violence for survival.”, shared Murindanyi Sudi from Uganda, in the early days of the pandemic.

Zaheeda Tshankie expressed her worries regarding South Africa, “A huge disparity in my country is the contrast between the poor and those who are middle-class and above. Most poor communities are more concerned about their next meal, not a virus.”

We need to act, now

The pandemic has shown us that dealing with its challenges on a global scale is fiendishly difficult. Recovery of these severe setbacks to human development and the poverty gap has to be mitigated by a different economy post-COVID.

As Dawid Mondrzejewski mentions about Poland,

“We are an economy that functions predominantly on relatively cheap labor. Unemployment is low, but most salaries are also small. I am worried if killing the economies is worth it if we so laxly approach the support for the possibly affected? Hopefully, around the world, fewer people will die from the economic slump, than from the virus.”

But even after the harsh effects of the pandemic, people are hopeful that the situation can be overcome through solidarity and innovation. They are taking matters into their own hands as indicated by Dev Bharti from the UK who says, “I feel our biggest challenge will be to try and restore balance in nature (not just talk) using innovative means, else nature will find ways such as this pandemic to balance things out. And it is crystal clear that this change needs to come bottom-up from people themselves, as the top-down approach has not worked!





Serhiy Shekhovtsov from Ukraine is using his skills to improve healthcare,

“I can see a lot of reasons to stay optimistic here. The whole world is fighting this together. I think one of the best ways to deal with stress and anxiety is to get yourself involved in the fight. I am building a free AI assistant for medical imaging. Hopefully, it will help many doctors someday.”

Solving wicked problems together

Be it the movements that started like #MasksForAll of the COVID-19 Solidarity Response Fund for WHO, people have come together to support each other in ways never seen before. There is a common feeling of solidarity and “being in this together” that is empowering collaborators from all around the world to develop solutions for these wicked problems.

“A wicked problem is a social or cultural problem that is difficult or impossible to solve for as many as four reasons: incomplete or contradictory knowledge, the number of people and opinions involved, the large economic burden, and the interconnected nature of these problems with other problems.”

Going by the definition, COVID-19 is definitely a wicked problem. It is a storm in which we are all together, but in different boats, some rockier than the other. Challenging issues or problems often take time and vast amounts of resources to get solved. Sometimes thorny problems get solved quickly and without a whole lot of means. Through the diversity of thought, passion for the task at hand, and swift learning. In other words, through collaborative innovation.



Photo from Getty Images


Collaborative innovation is a way to tap into the passions of Guts, Glory, and Gold.  A space to try lots of ideas and embrace different perspectives; where there is freedom of thought and exploration. Such diversity allows us to examine any problem in multiple ways and gives birth to innovative solutions.

At Omdena, most of our problem statements are wicked problems. The future lies in solving the issues that matter. Technology is not the end. It is a means to an end. We need changemakers, people who have a broad set of skills and can solve multi-disciplinary problems, collaboratively.


Domestic Violence - The Shadow Pandemic of COVID-19

Domestic Violence - The Shadow Pandemic of COVID-19


By Omdena Collaborator Elke Klaassen



The Problem: Effects of policy measures on the vulnerable population


To prevent the spread of Covid-19, many governments have been taking strict measures such as closing borders, imposing nationwide lockdowns, and setting up quarantine facilities. While these measures may ensure that social distancing is followed seriously, they may have indirect effects on the economy and adverse effects on the well-being of people, especially the vulnerable population. To help governments make data analysis-driven policy decisions to effectively deal with issues like during COVID-19 like Domestic Violence, Omdena provided an enabling platform to AI experts, data scientists, and domain experts so that they could study the effects of Covid 19 policy measures on the vulnerable population. This article describes the results of one of many facets of this challenge, which focused on the impact of Covid-19 on domestic violence using Data Analysis.

The goal of this task was to get a better grip on domestic violence during COVID-19 and gauge the scale of the problem. To this end, different data sources were used — including news articles, policy data, mobility trends, and domestic violence search rates. The results indicate that the problem of domestic violence could be much bigger than indicated by some of the key figures mentioned in the news. Further, restrictions on movement and strict enforcement of lockdowns may have further amplified the issue. It can be said that domestic violence is a shadow pandemic and it is integral to understand the gravity of the problem and ensure redressal and support to survivors and vulnerable populations.



Domestic violence — a growing shadow pandemic of COVID 19

The UN Women recently labeled the increase of violence against women as ‘a growing shadow pandemic’. As a consequence of Covid19 policy measures, many victims find themselves in proximity to their abusers due to lockdown measures. The world is witnessing a sharp rise in the number of helpline calls, domestic violence reports, as illustrated in the following infographic. This highlights the pressing need to reflect upon the pre-existing and growing incidence of domestic violence and sensitizing organizations and communities at the grassroots level to provide help and support.



Infographic on Covid19 and domestic violence adapted from the UN Women.

Infographic on Covid19 and domestic violence adapted from the UN Women.




The shadow pandemic’s size— news coverage

The news is replete with reports and cases of domestic violence and its surge during the pandemic. During March beginning, the increase in domestic violence in China received coverage in the news. In the Hubei Province the number of reported cases had tripled in February, compared to the same period last year. Weeks later, similar articles appeared from all over the world.

To get the first grip on gravity and spread of this shadow pandemic, a dataset of about 80,000 Covid-19-related news articles was used. This dataset was created using GDELT to query relevant articles and news-please to extract contents. The said dataset has been used for different analysis in the Omdena AI pandemic challenges. To identify the news articles related to domestic violence, the corpus was filtered based on domestic violence-related keywords. In total 1,500 articles were linked to both Covid-19 and domestic violence  using Data Analysis revealing a connection.



Covid19 and domestic violence-related articles

To assess the relevance of the subset of domestic violence-related news articles, LDA topic modeling was performed, using gensim. Three topics were modeled, and one of these clearly illustrates that the considered subset covers domestic violence. The world-cloud of this topic is shown in the figure.


Graph between Number of news articles and Date

Number of both Covid19 and domestic violence-related news articles over time.


The absolute increase in domestic violence-related articles

The number of news articles related to both Covid-19 and domestic violence started to increase a couple of weeks after the first lockdown measures were implemented in Europe (end of February).


Relative increase

The increasing trend in domestic violence-related articles could be explained by an overall increase in Covid-19 related articles. To study whether the topic of domestic violence has become more dominant in the discussion, the ratio of domestic violence-related articles versus the total number of Covid-19 related articles is illustrated. An increasing trend can be observed using Data Analysis, indicating that the issue of domestic violence has become more dominant post the onset of the pandemic.



Graph between Ratio of Domestic Violence News Articles and Date

Domestic violence-related news articles are relative to Covid19 related news articles.



The shadow pandemic’s size — search rates

The data mentioned in the news is typically in summary form, similar to the key figures shown in the Infographic of UN Women. To get a more detailed grip on the extent and size of the shadow pandemic, different datasets were used:

  • Policy data:
    OXFORD COVID-19 Government Response Tracker (OxCGRT), covers the policy measures taken in 152 countries (accessed on May 8, 2020).
  • Mobility data:
    Google COVID-19 Community Mobility Reports, indicate the percentual changes in mobility patterns in 132 countries (accessed on May 8, 2020). The data is relative (_rel) to the mobility patterns between January 7 and February 7, 2020. To limit stochasticity, a moving average (_ma) filter of 7 days (1 week) was applied.
  • Search data:
    Google Trends data, indicates the search trend of a certain topic over time (accessed on May 8, 2020). To get the percentual change (_rel) in search rates, this date is made relative to a baseline period as well (Jan 3 — Feb 13). To remove stochasticity a moving average filter (_ma) of 14 days (2 weeks) was applied to the Google Trends data.


The data analysis focuses on countries that are present in all three datasets, and that have sufficient Google Trends data available. The condition of having data available for at least 50% of the considered time period (Jan 3 — May 8) was imposed. This ensured that the analysis was expansive and included a total number of 53 countries.

The search trend data is considered to be relevant for studying the scale of the problem in situations where one is in search of help, has access to the internet, and has a certain level of trust in societal organizations to be able to offer help. Evidently, the last two conditions are not met in different countries to the desired level across the world. This is, amongst others, reflected in the Human Development Data — for example, the % of the (female) population that has access to the internet. Hence, the results should be considered with these conditions, caveats, and nuances in mind.

Further, the use of search rates has a clear advantage. The victim’s quest for help and receiving help is expected to consist of several steps; and more courage is required for every succeeding step that needs to be taken. The most basic step might be to browse the web for ways to deal with and seek help for domestic violence. Hence, search rate data might reflect the scale of the real problem more accurately than the number of domestic violence reports, because the search rate is probably the first step a victim might take in seeking assistance. 


Correlation between policy measures, mobility, and domestic violence search rates using Data Analysis


The first step in the analysis is to study correlations between the different features in the dataset. The correlation plot for France is shown below. A highly negative correlation (-0.95) between workplace mobility and domestic violence search rates can be observed. And, as expected, workplace mobility highly correlates with the workplace closing policy measure that was implemented by the government.



Correlation plot of the different features of the policy, mobility, and search rate dataset (France).

Correlation plot of the different features of the policy, mobility, and search rate dataset (France).



Graph between Search Trend and Mobility Change and Date

Policy measures, mobility, and search rate trends over time (France).


In the figure, the trend of workplace mobility and domestic violence search rates is visualized over time. The negative correlation between both variables is illustrated by the decrease in workplace mobility, while at the same time there is an increase in domestic violence search rates. Compared to the baseline, search rates almost doubled (100% increase). This indicates that the incidence of searching for information related to domestic violence increased with the decline in workplace mobility and as people found themselves stuck at home.


Regression models to quantify the effect of mobility on domestic violence search rates

Regression models were used to assess the size and significance of the relationship between workplace mobility and domestic violence search rates.


Regression model results of the impact of mobility on domestic violence search rates (France).

Regression model results of the impact of mobility on domestic violence search rates (France).


The linear line in the scatter plot is the illustration of the output of the regression model for the case study of France. The relationship between mobility and domestic violence is significant, and the slope indicates that with every 1% decrease in mobility, domestic violence search rates increase by 1.4%.

The results of the models for the countries in the top 10 and bottom 10 are listed below. In the top 10 countries, decreasing mobility correlates with a steep increase in domestic violence search rates. In the bottom 10 countries, the opposite trend is observed: mobility and domestic violence both decrease at the same time. To further study and explain the results of the different models, the individual plots for the first six in the categories of the top 10 and bottom 10 countries are shown in the next section.



Tabular format describing top 10 countries to bottom 10 countries defining Pvalues, Coefficient, Country, and Significance.



Countries illustrating a strong relationship between a decrease in mobility and an increase in domestic violence

The individual figures for the first six among the top 10 countries are shown. These countries have a strong relationship between mobility decrease and domestic violence increase.


Graph Between Search Trend and Mobility Change % vs date for 6 countries namely, Vietnam, Japan, South Africa, Germany, France, and Belgium.


  • With the exception of Japan, the peak in search rates has doubled or even tripled in each of the illustrated countries.
  • Although the coefficient in Japan is relatively high, the peak in search rate is ‘just’ 60%. This is due to a relatively limited decrease in mobility, likely due to less strict lockdown measures in this country.
  • Vietnam stands out with a peak in domestic violence search rates that increased by more than triple the baseline. The issue of domestic violence in light of social distancing in Vietnam is stressed in this article as well, stating that the number of people who are in need of shelter has doubled compared to 2018 and 2019.
  • The figures for Germany, France, Belgium, and South Africa, clearly illustrate the increasing trend in domestic violence search rate as mobility drops.


Countries not illustrating a relationship between a decrease in mobility and an increase in domestic violence

The individual figures for the final six countries among the bottom 10 countries are displayed below and show a positive relationship between mobility and domestic violence.


Graph Between Search Trend and Mobility Change % vs date for 6 countries namely, Australia, Thailand, South Korea, Jamaica, El Salvador, and Philippines.


  • First of all, the plot for Australia stands out, which witnessed a high increase in domestic violence towards the end of February. The sudden rise in domestic violence in Australia is assumed to be a consequence of the bushfires which occurred around this time. This relationship is also expressed in this article: ‘the bushfires’ hidden aftermath: Surging risk of domestic abuse
  • In South Korea, lockdown measures could be considered to be more targeted instead of strict blanket measures, and this could explain the unique trend displayed for this country as compared to the others.
  • For the Philippines, Thailand, El Salvador, and Jamaica, the simultaneous drop in domestic violence search rates and mobility is visible. This does not mean that there have been fewer domestic violence incidents. There can be various other factors influencing the observed search rate trends. For example, the peaks in search rates in these countries towards the late February / beginning of March could be explained by the (media) attention given to domestic violence in light of International Women’s Day on March 8. there was a large turnout for the different marches that were held that day, both in Asia and Latin America.


Action is needed to mitigate the increase in domestic violence

This article studies the impact of the Covid-19 global pandemic on domestic violence. The increase in domestic violence can be viewed as the ‘growing shadow pandemic’. This is stressed by the news as well — there is an increasing trend in the number of articles that cover the issue. Some of these articles give insight into the gravity and scale of the ‘growing shadow pandemic’ in summary form. For example, the Infographic of UN Women, shown at the beginning of this article, mentions that in France, Argentina, Cyprus and Singapore domestic violence emergency calls and reports have increased by more than 30%.


The results indicate that the problem of domestic violence could be much bigger than indicated by some of the key figures in the news
The Data analysis of Google mobility and search rate trends shows that the effect of lockdown measures on domestic violence, such as the closing of workplaces, can be much higher than 30%. In countries where the inverse relationship between the decrease in mobility and increase in domestic violence is strongest, search rates have doubled, and some more than tripled. A search query could be considered the most accessible step in seeking out help. This could explain why the results in this article indicate that the problem of domestic violence could be much bigger than the previously mentioned key figures.

It is important to note that there are many other factors that can influence the search rate results. The extent to which the search rates may accurately reflect the growing scale of the problem of domestic violence also depends on the situation the countries are in. As stated before, a victim is only expected to perform a search query if s/he has access to the internet and a certain level of trust in societal organizations to be able to offer help. These assumptions could explain that a strong relationship is found in many European countries in this study.

The aim of this work is to help build awareness on the issue of domestic violence. Although some countries have adopted steps to mitigate problems, the results clearly indicate that the issues persist. In this light, the UN recently published a brief with ‘recommendations to be considered by all sectors of society, from governments to international organizations and to civil society organizations in order to prevent and respond to violence against women and girls, at the onset, during, and after the public health crisis with examples of actions already taken’.




More About Omdena


Omdena is an innovation platform for building AI solutions to real-world problems through the power of bottom-up collaboration.


| Webinar | Can Artificial Intelligence Help to Build A Better Future?

| Webinar | Can Artificial Intelligence Help to Build A Better Future?

A vibrant and insightful discussion on how to define an impactful AI use case (framework below), how AI technology can help during COVID19, why we might be losing our voice during lockdowns, and how to overcome this. Most importantly we discussed how we as citizens and communities can take action to build a better future. Make sure to read the key points below and check out the entire recording at the end of the blog post.


Master Inventor Neil Sahota takes the stage

Our fireside guest Neil Sahota is a sought-after global expert who has worked with Global Fortune 500 companies, world government leaders, and startups around the world. He has been on panels with world-known business leaders like Gary Vaynerchuk and he creates value as a United Nations AI Expert, Master Inventor, and best-selling author.

What constitutes an impactful AI use case?

Focus on solving a problem and creating value, then ROI will follow.

In the first part of the webinar, we addressed the question of what value creation means in the context of AI.

Creating tangible results requires experimentation and breaking with old and conventional thinking habits that are deeply rooted in many organizations. AI is a disruptive technology and with all disruptive technologies, there is an exploration phase and maturity phase. It is the decision of the company to be part of it or miss the accelerating AI train.

Everyone is talking about automation while the real value lies in building innovative solutions where technology is paired with human creativity.


AI Innovation at Omdena

Copyright: Neil Sahota


The magic formula for impactful AI use cases

AI is not the solution to all problems. Building products does not start with thinking about AI but finding a meaningful problem that once solved adds value for the customer or user. Many organizations fall into the trap of adding AI to their strategy without first defining the problem in detail.

According to Neil defining a use case successfully comes with two key ingredients. The right mindset of entrepreneurial thinking, stepping away from “why it won’t work” to “how to make something work”. Next, we need to dive into what are the real problems and root causes to derive a clear problem statement. Only after doing this, we can explore further through knowledge of the space, Rules/regulations, adoption challenges to identify if there is an opportunity or not. Next, the technical implementation starts to build an actual solution. If you are interested, you can find real-world use cases here.

Neil Sahota Omdena


Use cases of AI for COVID19

We addressed the following use cases in the webinar:

  • AI-driven monitoring tools for social distancing
  • Cracking COVID-19 genetic signatures through Machine Learning
  • Looking at the effects of policies for vulnerable populations

What about domestic violence during a lockdown?

One observation during our AI project about how policies and lockdowns affect vulnerable populations was a spike in domestic violence. Below Rudradeb Mitra touches on the example of Singapore. If you are interested in other countries, check out this article.

AI Covid19

Domestic Violence Singapore


Chances for organizations during COVID19

As Omdena Founder Rudradeb Mitra points out the current crisis shows who is affected the most or in other words who is most vulnerable. This can also be applied to customers, users, and even employees where organizations can use AI technology like sentiment analysis to understand which subgroups are most affected by a regulation or policy.


How can we build a better future

Lastly, we discussed how each one of us can make a difference by using his or her voice. There are no experts of the future and the only way to predict the future is to create it. What can each one of us do to create a better future is a question we all need to ask ourselves!

Here is the entire outline of the webinar:

  • Min 3:00: Introduction by Neil Sahota: How to build an impactful AI use case
  • Min 13:15: Opportunities for organizations, increase of domestic violence
  • Min 23:05: Fireside chat: Use cases, how to overcome AI bias, how to build solutions as communities rather than relying on governments and large organizations, etc.

To be updated on our next webinar sign up here.

About Omdena

Omdena is an innovation platform for building AI solutions to real-world problems through the power of bottom-up collaboration.



Estimating Possible Undetected COVID-19 Infection Cases using Probability Analysis

Estimating Possible Undetected COVID-19 Infection Cases using Probability Analysis

Country-wide estimations for undetected Covid-19 cases and recommendations for enhancing testing facilities based on Probability Analysis

The Problem: Why estimating undetected Covid-19 cases is crucial?

An estimation of the undetected Covid-19 cases is important for authorities to plan economical policies, make decisions around different stages of lockdown, and to work towards the production of intensive care units.

As we have crossed a psychological mark of 1 million Covid-19 patients around the globe, more questions are popping up regarding the capabilities of our health care systems to contain the virus. One of the major worries is the systematic uncertainty in the number of citizens who have hosted the virus. The major contribution to this uncertainty, i.e. Probability Analysis, is possibly due to the small fraction of Covid-19 tests being performed.

The main test to confirm if someone has Covid-19, is to look for signs of the virus’s genetic material in the swab of their nose or throat. This is not yet available for most people. The healthcare workers are morally restricted to reserve the testing apparatus for seriously ill patients in the hospital.


The Solution


In this article, we will show a simple Bayesian approach, a part of Probability Analysis to estimate the undetected Covid-19 cases. The Bayes theorem can be written as:

P(A|B) = P(B|A) × P(A) / P(B)

where P(A) is the probability of event A, P(B) is the probability of event B, P(A|B) is the probability of observing event A if B is true, and P(B|A) is the probability of observing event B if A is true.

The quantity of interest for us is P(infected|notTested) i.e. the probability of infections that are not tested. This is equivalent to the percentage of the population infected by Covid-19 but not tested and we can write it as:

P(infected|notTested) = P(undetected|infected)×P(infected)/P(not tested)

Here the other probabilities are:

  • P(notTested|infected): Probability of tests not done on people that are infected or percentage of the population not tested but infected.
  • P(infected): Prior probability of infection or known percentage of the infected population.
  • P(not tested): Probability or percentage of people not tested.

The following plot shows the total Covid-19 tests per million people and the total number of confirmed cases per million people for several countries. This suggests a clear relation between the Covid-19 tests and confirmed positive detections.


Test per million vs Positive per million graph

Figure 1: Tests per million versus positive Covid-19 cases per million as of 20 March 2020 (data source).


Assuming that all countries follow this relation between the Covid-19 tests and confirmed cases, we can make a rough estimate of the number of undetected cases in each country by using Probability Analysis in every country.


Let’s take Australia as an example:

For example, the plot shows that prior knowledge of infected cases

P(infected) = 27.8/10⁶, and

P(not tested) = (10⁶ — 473)/10⁶.

To estimate the P(notTested|infected), I used the relation between the Covid-19 tests and confirmed cases as in the above Figure 1. This is done by fitting a power law of the form: y = a * x**b, where a is normalization, and b is the slope of this power law. The following plot shows a fit to the data points from the above plot, where the best fit a = 0.060±0.008 and b = 0.966±0.014.


Test per million vs positive per million graph 2

Figure 2: The relation between Covid-19 tests and confirmed cases and a power-law best fit.


Using the best fit parameters, P(notTested|infected) = (10⁶— 4473)/10⁶ / (a * (10⁶ — 4473)**b)/10⁶.

With probabilities 1, 2 and 3, I find P(infected|notTested) = 0.00073 per cent population of Australia. Multiplying this by the population of Australia indicates that there is a possibility of about 18,600 undetected Covid-19 cases in Australia (Probability Analysis report). The following plot shows possible undetected Covid-19 cases as a function of tests per million for different countries as of 20 March 2020.


Tests per million vs Undetected Covid-19 cases graph

Figure 3: Estimation of undetected Covid-19 cases (see assumptions in the text).


Note that several assumptions and considerations are made to estimate these undetected cases. For instance:

  • I assumed that all countries would follow the same power-law relation to estimating P(notTested|infected). However, this is not an extremely good assumption as there is huge scatter in this relation between different countries.
  • Our prior knowledge of the number of infections can be biased itself as P(infected) depends on the number of tests performed as of 20 March 2020.
  • I haven’t considered the susceptibility of a country’s populations to Covid-19, and the attack rate i.e. the biostatistical measure of the frequency of morbidity, which for Covid-19 is estimated around 50–80% (Verity et al. 2020).
  • The impact of government policies of these countries from 14 days before 20 March and 14 days after is not considered.
  • I haven’t considered how susceptible people are targeted for testing in different countries in the next days.

Figure 4 below shows the total number of confirmed cases versus the tests per million as of 5 April 2020 for several countries (data source).

After 16 days on 5 April, the confirmed positive cases in countries like Ukraine, India and Philipines are consistent with the predictions in Figure 3. These countries performed ≤ 10 tests per million people as of 20 March.

Note that the consistency between estimations as of 20 March and 5 April does not necessarily mean that all undetected cases as of 20 March are confirmed now. Several of the confirmed cases as of 5 April are expected to be new cases due to the spread between 20 March and 5 April (even in the presence of lockdowns).

The estimated undetected cases for countries like Colombia and South Africa are about twice as large (Figure 3) as compared to the total confirmed cases as of 5 April (i.e. about 1,500 for both). Both countries have performed about 100 tests per million people.

Countries like Taiwan, Australia, and Iceland, on the other hand, have shown an order of magnitude small number of confirmed cases as compared to estimated numbers in Figure 3.

This indicates that the countries that have not boosted their testing efficiency to more than 1,000 tests per million people have significantly larger uncertainties on the number of current confirmed cases.


Tests per million vs Total positive cases graph

Figure 4: The total number of confirmed cases versus the tests per million as of 5 April 2020.


Given the data in Figure 4 from 5 April 2020, I repeated the whole exercise again to estimate the undetected Covid-19 cases for these countries, cities, and states. The following figure shows the best fit power-law and data points similar to Figure 2 but for the data as of 5 April 2020.


Tests per million vs Positive per million graph

Figure 5: Best fit power law for data as of 5 April 2020.


The best-fit slope for the power-law relation in Figure 5 (b = 1.281±0.009) is consistent with the slope in Figure 2 at the 2-σ confidence level. This helps our assumption of estimating P(notTested|infected) from the best fit power-law relation (the slope is not changing), however, other caveats are the same as before.

Finally, the following plot shows the estimated undetected Covid-19 cases for different countries as of 5 April 2020.


Tests per million vs undetected covid-19 cases graph

Figure 6: Estimated Undetected Covid-19 cases as of 5 April 2020 (see assumptions in the text).


As the comparison between the undetected estimations as of 20 March (Figure 3) and confirmed cases as of 5 April (Figure 4) shows that more tests per million people are required to capture the possible undetected cases, thus now is the high time that authorities raise the testing efficiency in order to reduce the systematics from undetected Covid-19 cases. This seems to be the only good way to reduce the death rate of Covid-19 patients as indicated by a large amount of Covid-19 testing in Germany and South Korea.

To make this happen, all countries need at least one testing center within a radius of 20 Km and arrange more drive through testing facilities as soon as possible.



More About Omdena

Omdena is an innovation platform for building AI solutions to real-world problems through the power of bottom-up collaboration.

How a Global Community Applies AI to Help Vulnerable Populations during COVID19

How a Global Community Applies AI to Help Vulnerable Populations during COVID19

A global team of changemakers applies AI to develop more inclusive government policies during pandemics.


By Omdena Founder Rudradeb Mitra

When travel is restricted, schools closed, businesses shut down, and communities put into quarantine, people lose income, employment, and access to healthcare and food.

While enforcing these lockdowns, are Government policies around the world taking into account the poorest and the most vulnerable?

A question we are answering in our Coronavirus Policy AI project with 70 collaborators from around the world.

Our first point of analysis was to look into some of the harmful side effects of the lockdowns.


Unintended consequences of the lockdown

#1 Increase in domestic abuse

In the first three weeks of the lockdown domestic abuse killings in the UK more than doubled [1], Childline India helpline received more than 92,000 SOS calls asking for protection from abuse and violence in 11 day which is an increase by 50%[2], Lebanon and Malaysia, for example, have seen the number of calls to helplines double, compared with the same month last year; in China, they have tripled, in France increase by a third [3]

“ It heightened the danger for women forced to stay at home with their abusers. Children are now even more exposed to trauma.”


#2 Poor kids do not have access to food

120 Million poor kids get their midday meal in India alone from their schools. This is often the only source of healthy food for those children. Closing schools will deny these children access to food. Feeding children that usually would get their lunch at school is also a problem in developed countries. For example, US food banks have seen a huge spike in need and estimate it will need an additional $1.4 billion to meet increased needs over the next six months [5].


#3 Increase in forced child marriage

During Ebola, it was seen that there was an increase in forced child marriage[6]. The same is expected during the Coronavirus lockdown.

Those are only a few examples out of many devastating consequences.

Looking at all the above, the question arises if government policies are inclusive and take into account the poor and vulnerable?

‘If you don’t address poverty, you can’t stop the virus,’

‘It’s almost as if some people think they can put a fence around the groups they left out’

‘Even when we take the rich countries, poor people know from history that every time there is some great struggle, whether it’s the Great War, or the Spanish flu, or the recession of 2008, they are hit the hardest’. [7]

Government policies cannot just look at stopping the spread of the virus but also have to look at how policies will directly impact people who are most vulnerable. There may be a fundamental problem in the current form of governance, which is top-down and lacks the ability to see the full picture.

‘The central planner is unable to obtain all the necessary information to organize society in this way, as information has subjective, creative, dispersed, and tacit qualities’ [8]


The Alternative: Bottom-up collaboration

To solve the current crisis (health, economic, humanitarian), we need a global effort that is sadly missing.

‘Be the change you want to see in the world’ — Mahatma Gandhi.

And this is what Omdena started doing.

Omdena is an innovation platform for building AI solutions to real-world problems through the power of bottom-up collaboration.

We gathered a group of 70 data scientists, AI/ML experts and domain experts from all over the world and across 6 continents. The experts are working (or worked) at the World Health Organization, The World Bank, European Commission, and UNICEF USA.

And the enthusiasm was clearly visible.



How AI can help to design inclusive policies

We have identified vulnerable populations based on the following criteria:

  • Limited access to health facilities
  • Wage loss
  • Employment loss
  • Facing domestic violence

We then created a Mathematical Formulation:

V — vulnerable populations (e.g. population weighted by poverty or accessibility index)

f(policy): impact of policy

F — resulting in the financial state of a vulnerable population (e.g. has job / daily earning)

H — resulting in the health state of a vulnerable population (e.g. COVID 19 — deaths/infections)


Equation proposed by Arthur Wandzel


We broke down the problem into multiple tasks, below are some of the results (we will publish all the results at the end of May).


Task 1: Identify the list of countries

task-managed by Alan Ionita

We are looking at different countries based on metrics like UN income classification, the Human Development Index, and the Inequality-adjusted Human Development Index (IHDI).


Inequality-adjusted HDI. Shared by Mauricio Calderon


Task 2: Access to health facilities

task-managed by Rohet Sareen


Work by Nikolaus Siauw


The data consisted of aggregated features related to Access to Health care facilities for certain countries. Features like Health Expenditure, Critical Beds, Physicians as well as Income Class of Country ( as per GDP) were used to account for each country’s healthcare using a variety of data sources.

The key objective was to get a cluster of countries having similar health care facilities which can then propagate the task of policy building for the health-care domain. K-Means Clustering Method was used along with a Principal Component Analysis (PCA) Method to map it on a 2-D graph as shown below.


Work by Kushal Vala


As we can infer from the graph that, certain countries sharing similar demographics and economic condition were clustered together.
The next step is to study each cluster and refine the model using different approaches and tuning the parameters.


Task 3: Domestic Violence

task-managed by Elke Klaassen

We also looked at the average search for child abuse and domestic violence after and before policy.


Work by Aaron Ferber


Task 4: Loss of employment

task managed by Baidurja ‘Adi’ Ray

In India, we see a somewhat bigger rise in unemployment (percentwise) for the urban region compared to the rest of the country but recently came back down — perhaps due to migration.


Work by Aaron Ferber


Task 5: List of policies and their effect

task manager by Kritika Rupauliha



Work by Arthur Wandzel


This is an ongoing work and above are only some of the results. At the end of May, we will publish all results including co-relation models.



In these difficult times, we at Omdena are optimistic about the future. We want to work towards building a future where not only the rich and powerful have a say but everyone’s voice is taken into account. A world that is driven by empathy and care for everyone and where a global community using advanced technologies like AI solves real-world problems for the people, by the people.

In conclusion, a quote that I will remind everyone at this time:

“Any society that would give up a little liberty to gain a little security will deserve neither and lose both” — Benjamin Franklin

I would like to thank Mauricio Calderon Chris P. Lara Neeraj Mistry Branka Panic Virginie MARTINS de NOBREGA for expert advice.

Here are some of the collaborators in this project (in alphabetical order):

Aaron Ferber, Ajaykumar G P Palaniswamy, Alan Ionita, Albina Latifi, Anis Ismail, Anju Mercian, Arthur Wandzel, Baidurja Ray, Bushra Akram, Cesar Velásquez, Elke Klaassen, Farhad Sadeghlo, Hassan Shallal, Hunar Batra, Kritika Rupauliha, Kunal Sinha, Kushal Vala, Magdalena Kalbarczyk, Mbithe Nzomo, Mircea Ioan Calincan, Mohammed Ba Salem, Nikhel Gupta, Nikolaus Siauw, Reem Mahmoud, Rohet Sareen, Sanchit Bhavsar, Shubham Mahajan, Sridatt More, Yash Bangera.


Omdena’s Covid19 initiative in NASDAQ billboard at Times Square NYC


About Omdena

Building AI Solutions Collaboratively 

Omdena is an innovation platform for building AI solutions to real-world problems through the power of bottom-up collaboration.

Learn more about the power of Collaborative AI.











Stay in touch via our newsletter.

Be notified (a few times a month) about top-notch articles, new real-world projects, and events with our community of changemakers.

Sign up here