<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Erika Russi on Medium]]></title>
        <description><![CDATA[Stories by Erika Russi on Medium]]></description>
        <link>https://medium.com/@erika.russi?source=rss-be9eb683b3b3------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/0*RcPgvasBfu3DgNbB</url>
            <title>Stories by Erika Russi on Medium</title>
            <link>https://medium.com/@erika.russi?source=rss-be9eb683b3b3------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Wed, 18 Nov 2026 17:13:20 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@erika.russi/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[The Data Behind the Job Search]]></title>
            <link>https://medium.com/@erika.russi/the-data-behind-the-job-search-39065bb3cdd7?source=rss-be9eb683b3b3------2</link>
            <guid isPermaLink="false">https://medium.com/p/39065bb3cdd7</guid>
            <category><![CDATA[job-hunting]]></category>
            <category><![CDATA[job-application]]></category>
            <category><![CDATA[resume-writing-tips]]></category>
            <category><![CDATA[data]]></category>
            <category><![CDATA[data-science]]></category>
            <dc:creator><![CDATA[Erika Russi]]></dc:creator>
            <pubDate>Mon, 21 Jan 2019 02:54:50 GMT</pubDate>
            <atom:updated>2020-11-01T18:44:53.134Z</atom:updated>
            <content:encoded><![CDATA[<p>TalentWorks has an excellent blog series called <a href="https://talent.works/blog/category/science-of-the-job-search">The Science of the Job Search</a>. Below are some of the best tips backed by their data analysis. Please note that this blog is not an endorsement of any of their products, but rather a genuine admiration and interest in the data science behind the job search.</p><h3>1. You don’t need to meet all the Job Requirements</h3><p>Based on TalentWorks’ analysis of 6,000+ applications across 118 industries:</p><ul><li>Once you meet 30% of job requirements, your chances of getting an interview begin to rise</li><li>But once you meet just 50% of job requirements, you’re not any more likely to get an interview</li><li>And for women, once they meet <em>40% of job requirements</em>, interview chances are roughly the same as they would be if they met a higher percentage of job requirements</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*cB2gGEbWuLQDCuDe" /><figcaption><a href="https://talent.works/blog/2018/11/27/the-science-of-the-job-search-part-vii-you-only-need-50-of-job-requirements/">https://talent.works/blog/2018/11/27/the-science-of-the-job-search-part-vii-you-only-need-50-of-job-requirements/</a></figcaption></figure><p>This is great news for women, who tend to dismiss jobs when they don’t meet all the requirements. Men will typically apply for a job after meeting 60% of the qualifications on the job description, while women only tend to apply after <a href="https://hbr.org/2014/08/why-women-dont-apply-for-jobs-unless-theyre-100-qualified">meeting all of the qualifications</a>.</p><p>There’s some more great news for women also shown in the graph above: being a woman gives you higher chance of getting an interview. According to a different TalentWorks analysis of 4,000 jobs, <a href="https://talent.works/blog/2018/01/08/the-science-of-the-job-search-part-i-13-data-backed-ways-to-win/"><strong>having an obviously female name gives you a 48% boost</strong></a>.</p><h3>2. Age matters</h3><p>It might be illegal, but age discrimination definitely exists.</p><p>According to TalentWorks’ analysis of 4000+ applications, the best age to get a job is between 28 and 35. After you reach 35, your chances of getting an interview drops by 8% every year.</p><p>Of course, you’re not listing your age on your resume, so the “age” here is your inferred age based on your graduation date and how much experience you have. TalentWorks advises not to list your graduation date if you’re older than 35.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/900/0*aTBy2Tt4ehM7hoEv" /><figcaption><a href="https://talent.works/blog/2018/01/08/the-science-of-the-job-search-part-i-13-data-backed-ways-to-win/">https://talent.works/blog/2018/01/08/the-science-of-the-job-search-part-i-13-data-backed-ways-to-win/</a></figcaption></figure><h3>3. When to Apply</h3><p>If you submit a job application in the first four days of the job being posted, you’re up to 8x more likely to get an interview. After that, every day you wait reduces your chances by 28%.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/864/0*5e3nnICVjQ1x4mWr" /><figcaption><a href="https://talent.works/blog/2017/09/28/getting-ghosted-on-your-job-applications-heres-fix-1-apply-within-96-hours/">https://talent.works/blog/2017/09/28/getting-ghosted-on-your-job-applications-heres-fix-1-apply-within-96-hours/</a></figcaption></figure><p>Applying on Mondays helps your chances of getting an interview, while applying on Fridays gives you the worst chances.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/900/0*nAHvfDa2fpGBvNQk" /></figure><p>TalentWorks analyzed a subsample of 1,610 applications to see how much time of day affects your likelihood of scoring an interview. The <strong>best time to apply for a job is between 6am and 10am</strong>. Afterwards, your interview odds start falling by 10% every 30 minutes.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*mYgROPRoi_c2wqXC" /></figure><h3>Tips for your Resume:</h3><h3><strong>1. </strong>Include (the right amount of) buzzwords</h3><p>In order to get filtered forward by automated screening tools, you need to use buzzwords specific to your industry. But there is a sweet spot. <strong>For most people, adding 15–20 skills, buzzwords, acronyms, etc. </strong>to your resume helped their chances of getting an interview the most.</p><p>TalentWorks recommends using a buzzword every 3–6 sentences.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/900/0*Vr2eIlYldDcJA5qo" /><figcaption><a href="https://talent.works/blog/2018/01/08/the-science-of-the-job-search-part-i-13-data-backed-ways-to-win/">https://talent.works/blog/2018/01/08/the-science-of-the-job-search-part-i-13-data-backed-ways-to-win/</a></figcaption></figure><h3><strong>2. Show your achievements with numbers</strong></h3><p>Quantifying your past work sounds impressive and really helps you stand out among your competition.</p><p>The Muse has a great article on <a href="https://www.themuse.com/advice/how-to-quantify-your-resume-bullets-when-you-dont-work-with-numbers">how to quantify your resume</a>. Even if you think you don’t work with numbers, you can still absolutely add some numbers and data to your resume.</p><p>TalentWorks’ analysis backs up the importance of quantifying up to 40% of your achievements:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/900/0*MjDJZKgI4O9JLAmw" /><figcaption><a href="https://talent.works/blog/2018/01/08/the-science-of-the-job-search-part-i-13-data-backed-ways-to-win/">https://talent.works/blog/2018/01/08/the-science-of-the-job-search-part-i-13-data-backed-ways-to-win/</a></figcaption></figure><h3>3. Remove team-oriented words</h3><p>Unfortunately, collaborative language gets penalized if you use it too much on your resume. It may be difficult for a hiring manager to know exactly what you did when you “collaborate with” or “assist” a team. It’s also possible that team-oriented words may carry passive undertones.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/900/0*9klItd82IIRQo0w2" /><figcaption><a href="https://talent.works/blog/2018/01/08/the-science-of-the-job-search-part-i-13-data-backed-ways-to-win/">https://talent.works/blog/2018/01/08/the-science-of-the-job-search-part-i-13-data-backed-ways-to-win/</a></figcaption></figure><h3>4. Use leadership words instead</h3><p>Using strong leadership words gives you a better chance of getting an interview. Some of the words TalentWorks detected as strong, active words:</p><blockquote><em>communicated<br>coordinated<br>leadership<br>managed<br>organization</em></blockquote><p>TalentWorks recommends using leadership words every 5 sentences.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/900/0*nntN8RVY5NRhI7VM" /><figcaption><a href="https://talent.works/blog/2018/01/08/the-science-of-the-job-search-part-i-13-data-backed-ways-to-win/">https://talent.works/blog/2018/01/08/the-science-of-the-job-search-part-i-13-data-backed-ways-to-win/</a></figcaption></figure><h3>5. Start your achievements with Action Verbs</h3><p>The Muse has an <em>amazing</em> list of <a href="https://www.themuse.com/advice/185-powerful-verbs-that-will-make-your-resume-awesome">185 Action Verbs</a> to really make your resume pop and sound less repetitive.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/900/0*rhL3F4d43RV7qbVN" /><figcaption><a href="https://talent.works/blog/2018/01/08/the-science-of-the-job-search-part-i-13-data-backed-ways-to-win/">https://talent.works/blog/2018/01/08/the-science-of-the-job-search-part-i-13-data-backed-ways-to-win/</a></figcaption></figure><h3>6. Avoid personal pronouns</h3><p>Applicants who used <em>even one</em> personal pronoun in their employment section had a lower chance of getting an interview callback.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/900/0*R9tYKS31tgIyXI4Q" /><figcaption><a href="https://talent.works/blog/2018/01/08/the-science-of-the-job-search-part-i-13-data-backed-ways-to-win/">https://talent.works/blog/2018/01/08/the-science-of-the-job-search-part-i-13-data-backed-ways-to-win/</a></figcaption></figure><h3>7. Cap your resume at 600 words and one page</h3><p>Once your resume exceeds 600 words, your chances of an interview plummet.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*uXJ4ZOAiSUXhPr6H" /><figcaption><a href="https://talent.works/blog/2018/12/05/the-science-of-the-job-search-part-viii-your-chances-of-an-interview-plummet-if-your-resume-is-too-long/">https://talent.works/blog/2018/12/05/the-science-of-the-job-search-part-viii-your-chances-of-an-interview-plummet-if-your-resume-is-too-long/</a></figcaption></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=39065bb3cdd7" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Prosecutor’s Fallacy]]></title>
            <link>https://medium.com/@erika.russi/prosecutors-fallacy-cfa156b508c7?source=rss-be9eb683b3b3------2</link>
            <guid isPermaLink="false">https://medium.com/p/cfa156b508c7</guid>
            <category><![CDATA[criminal-justice-reform]]></category>
            <category><![CDATA[sally-clark]]></category>
            <category><![CDATA[prosecutors-fallacy]]></category>
            <category><![CDATA[bayes-theorem]]></category>
            <dc:creator><![CDATA[Erika Russi]]></dc:creator>
            <pubDate>Thu, 29 Nov 2018 18:34:19 GMT</pubDate>
            <atom:updated>2018-11-29T18:34:19.545Z</atom:updated>
            <content:encoded><![CDATA[<p>In my Data Science immersive course at Flatiron School, we recently learned about Bayes’ Theorem and its application to predict the probability of an event, based on prior knowledge of conditions that might be related to that event.</p><p>The rule is usually read as:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/460/1*34A_BY9LcvsuOdNlH5OxbA.jpeg" /><figcaption>Lady Justice and her best weapon: Bayes’ Theorem</figcaption></figure><p>Regrettably, in the criminal justice world, Bayes’ theorem is sometimes exchanged for the Prosecutor’s Fallacy and, in the process, leads to miscarriages of justice. Below, I will discuss a case that has become synonymous with the Prosecutor’s Fallacy.</p><p>In 1999, a British woman named Sally Clark was convicted of the murder of her first two children.</p><p>Three years earlier, Clark’s first child, Christopher, had died at the age of three months. The child’s death had originally been attributed to Sudden Infant Death Syndrome (SIDS). Then Clark’s second child, Harry, died just over a year later at the age of two months. Harry’s death was deemed suspicious by the forensic pathologist who performed the autopsy. The pathologist then revisited the first child’s death and determined that it too was suspicious. Sally Clark was arrested some weeks later and eventually convicted of the two deaths.</p><p>Based on SIDS rates in the UK, the prosecution’s witness argued that the probability of there being two such deaths in the same family was roughly 1 in 73 million.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/666/1*IOG3CkvHK5FqiWAokBUJ6A.png" /></figure><blockquote>“You have to multiply 1 in 8,543 times 1 in 8,543…approximately a chance of 1 in 73 million which would happen ‘by chance’ once every 100 years.”</blockquote><blockquote>— Prosecution Testimony of Sir Roy Meadow, Pediatrician</blockquote><p>There were two mistakes with this thinking:</p><h3><strong>1. </strong>Assumption of Independence</h3><p>Professor Meadow assumed that the deaths of the two Clark boys were independent. However, risk factors for SIDS are likely to be common to multiple children within a family and one SIDS death is actually known to <em>raise</em> the probability of another in the same family. In Meadow’s assessment, there was no consideration of a possible unknown, hidden cause existing which might make a particular family more vulnerable to SIDS.</p><p>Unfortunately, when this mistake was drawn to the attention of the judges at the first Court of Appeal hearing, they dismissed it as “[in]capable of affecting the safety of the convictions.”</p><p>The British Medical Journal published an article after the trial referencing other studies which suggested that SIDS deaths are not random events, and that “recurrence” of SIDS in the same family would be much more frequent than 1 in 73 million live births. Recurrence might even occur in England about once every 18 months, rather than once every 100 years.</p><h3><strong>2. The Prosecutor’s Fallacy</strong></h3><p>The second mistake arising from Professor Meadow’s evidence as to probabilities is known as the Prosecutor’s Fallacy.</p><p>This consists of showing that the “innocent” explanation for certain facts is highly improbable – and then deducing that the “guilty” explanation is therefore the correct one.</p><p>So if H is <em>Sally Clark is Guilty</em> and E is <em>the Evidence of her two sons’ deaths, </em>the <a href="http://en.wikipedia.org/wiki/Prosecutor%27s_fallacy">prosecutor’s fallacy</a> hastily concludes that:</p><p><strong>P(H|E) = P(E|H)</strong></p><p>While Bayes’ Theorem states:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/492/1*ZCxaIOycEgYlHqqpUfmLaQ.png" /></figure><p>By equating P(H|E) with P(E|H), the prosecution completely ignored the prior (the probability of Sally’s guilt). But, we need the prior probability in order to nail down the posterior probability. So we need to ask: <em>How often do mothers murder their first two children within their first year of life?</em></p><p>Unfortunately for Sally Clark, this was not taken into account and she was sentenced to two life sentences.</p><p>In 2002, a Mathematics professor attempted to accurately compare the chances of the two possible explanations: Two successive deaths in the same family, both by SIDS; or a double homicide. He concluded that successive accidents are between 4.5 and 9 times more likely than are successive murders, so it was statistically more rare for a mother to kill both her children.</p><p>In 2003, evidence emerged that the forensic pathologist who had examined both babies had incompetently failed to disclose microbiological reports suggesting the second son had died of natural causes. Clark’s conviction was subsequently overturned. She was released from prison having served more than three years of her sentence. Clark died a couple of years later.</p><p><strong>Sources:</strong></p><ul><li><a href="https://en.wikipedia.org/wiki/Prosecutor&#39;s_fallacy">Prosecutor&#39;s fallacy - Wikipedia</a></li><li><a href="https://en.wikipedia.org/wiki/Sally_Clark">Sally Clark - Wikipedia</a></li><li><a href="https://rss.onlinelibrary.wiley.com/doi/pdf/10.1111/j.1740-9713.2015.00839.x">Royal Statistical Society Publications</a></li><li><a href="https://bayesian-intelligence.com/bwb/2012-03/sally-clark-is-wrongly-convicted-of-murdering-her-children/">Bayesian Intelligence</a></li><li><a href="https://understandinguncertainty.org/node/545">Convicted on Statistics?</a></li><li><a href="https://www.gaussianwaves.com/2013/10/bayes-theorem/">Bayes&#39; Theorem</a></li></ul><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=cfa156b508c7" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Benny and the (di)Gits!]]></title>
            <link>https://medium.com/@erika.russi/benny-and-the-di-gits-e6bb9f40c552?source=rss-be9eb683b3b3------2</link>
            <guid isPermaLink="false">https://medium.com/p/e6bb9f40c552</guid>
            <category><![CDATA[benfords-law]]></category>
            <category><![CDATA[plotly]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[fraud-detection]]></category>
            <category><![CDATA[pandas]]></category>
            <dc:creator><![CDATA[Erika Russi]]></dc:creator>
            <pubDate>Tue, 13 Nov 2018 11:01:02 GMT</pubDate>
            <atom:updated>2018-11-13T23:06:58.980Z</atom:updated>
            <content:encoded><![CDATA[<h3>Benford’s (and Newcomb’s) Law!</h3><p>Several years ago, I listened to a <a href="https://www.wnycstudios.org/story/91699-from-benford-to-erdos">Radiolab story</a> that really stuck with me. The theme for the entire episode was numbers, but more specifically, the program had a forensic accountant discuss how he could show someone had committed fraud using something called Benford’s Law.</p><p>Before there were calculators, mathematicians would have to do complicated math with the aid of logarithmic tables (example shown below). In 1881, an astronomer named Simon Newcomb, would carry out logarithmic equations using a book of these tables. He noticed that the earlier pages of the book (i.e. the tables for numbers 1, 2, 3) were more worn out than the later pages. This led Newcomb to form the principle that, in any list of “natural” numbers, more numbers will tend to begin with “1” than with any other digit. Newcomb considered natural numbers those numbers you would run into in the course of everyday life.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*xj-WeTPajDPrBh2l7InkQg.jpeg" /><figcaption><a href="https://en.wikipedia.org/wiki/Abramowitz_and_Stegun">https://en.wikipedia.org/wiki/Abramowitz_and_Stegun</a></figcaption></figure><p>Then, in 1938, a physicist working for General Electric named Frank Benford rediscovered Newcomb’s observations and came up with his eponymous Law.</p><blockquote>“<strong>Benford’s Law </strong>is the mathematical theory of leading digits. Specifically, in data sets, the leading digit(s) is (are) distributed in a specific, nonuniform way. While one might think that the number 1 would appear as the first digit 11 percent of the time (i.e., one of nine possible numbers), it actually appears about 30 percent of the time... Nine, on the other hand, is the first digit less than 5 percent of the time.” — <a href="https://www.isaca.org/Journal/archives/2011/Volume-3/Pages/Understanding-and-Applying-Benfords-Law.aspx">Journal of Information Systems Audit and Control Association (ISACA)</a></blockquote><figure><img alt="" src="https://cdn-images-1.medium.com/max/650/1*y2FVrNmTfQeA7iGEKqFrLQ.jpeg" /><figcaption><a href="https://www.isaca.org/Journal/archives/2011/Volume-3/Pages/Understanding-and-Applying-Benfords-Law.aspx?utm_referrer=">https://www.isaca.org/Journal/archives/2011/Volume-3/Pages/Understanding-and-Applying-Benfords-Law.aspx</a></figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/559/1*siBr-2O4stmmpRQ6vDiWzw.png" /><figcaption><a href="http://www.datagenetics.com/blog/march52012/">http://www.datagenetics.com/blog/march52012/</a></figcaption></figure><p><strong>Benford’s formula</strong> states that the probability of the leading digit being of a certain value can be described by this function.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/480/1*n5IplSh5Y6HZywJkRUL46Q.png" /></figure><p>In python, Benford’s formula would look like this and matches the frequencies by digit of the bar graph above.</p><p>Benford was able to validate his Law with <a href="https://en.wikipedia.org/wiki/Benford%27s_law">20 different sets of data</a>, including the surface areas of 335 rivers, the sizes of 3259 U.S. populations, 104 physical constants, 1800 molecular weights, 5000 entries from a mathematical handbook, 308 numbers contained in an actual issue of Readers’ Digest, the street addresses of the first 342 persons listed in American Men of Science, and 418 death rates.</p><p>As a (very new) data science student, I wanted to demonstrate Benford’s Law using my new python skills. Back in the 1930s, Benford pored over 20 different data types across countless days, maybe even months, or years. I could look at a pretty sizeable data set in an afternoon and see if it followed Benford’s Law.</p><p>These are the steps I took:</p><h3>1. Get some data!</h3><p>The type of data set itself didn’t matter too much. I opted for a large amount of data: Labor Force numbers from the <a href="https://data.worldbank.org/indicator/SL.TLF.TOTL.IN">World Bank</a>. The numbers went back a couple of decades and they were available by country, all in convenient CSV format. I used the <a href="https://pandas.pydata.org/">pandas library</a> to read the file and return numbers for 1990, 2000, 2010, and 2017.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/741/1*OaKZyP1L_R6wRS-Ozp3MxQ.png" /></figure><h3>2. Clean the data!</h3><p>After converting the table into a list of dictionaries, I noticed there were some pesky NaN results. What even is a NaN? I played around with some boolean functions and found a math.isnan function that helped me filter out any countries that had NaN results.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/832/1*lQDyvOTlHaTNU3mFti3blw.png" /></figure><p>I went from a data set of 264 countries to one with 232. Not a terrible loss.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/839/1*VS0f0YxRyBRBI6pHAOmaaA.png" /></figure><h3>3. Get those first digits and make tuples!</h3><p>I extracted all the first digits from every year’s data set and put them in a tuple per country. I didn’t track which country they were associated with because I just wanted to read the numbers.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/830/1*PKuofAdQYLJJ5xo-wlx-IQ.png" /></figure><h3>4. Put each year’s data into its own list!</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/818/1*8XKz0-EJqBuD_y1KXCBMvg.png" /></figure><h3>5. Calculate the frequency at which each number (1 through 9) occurs!</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/827/1*GXrQha2tVPMy6HcREQCKlQ.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/824/1*C6AOpCEeLdCFaE3GOfy-WQ.png" /></figure><p>And just because I now had a data set of 928 first digits, I calculated the total frequencies:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/831/1*T-Uy1iCA3BeKdNchqhN4RQ.png" /></figure><h3>6. Compare to Benford’s Law!</h3><p>Did my data match up to Benford’s Law? It was prrrretty close:</p><iframe src="https://cdn.embedly.com/widgets/media.html?url=https%3A%2F%2Fplot.ly%2F%7EErika-Russi%2F1%2F&amp;src=https%3A%2F%2Fplot.ly%2F%7EErika-Russi%2F1.embed%3Fautosize%3Dtrue&amp;type=text%2Fhtml&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;schema=plot" width="600" height="400" frameborder="0" scrolling="no"><a href="https://medium.com/media/494e4f4b45c2117426ec8745669951d6/href">https://medium.com/media/494e4f4b45c2117426ec8745669951d6/href</a></iframe><p>Benford’s Law is now being used more frequently. Lately, it has been applied in accounting fraud detection, admitted as legal evidence in U.S. criminal cases, and even used to show evidence of<a href="https://www.newscientist.com/article/mg20227144-000-statistics-hint-at-fraud-in-iranian-election/"> election fraud</a>. As a data scientist, it is a simple and handy formula to use to verify the reliability of your data.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=e6bb9f40c552" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>