Data Science Hiring Process at Khatabook

0


With over 10 million monthly active merchant users, Khatabook has become one of the best known names for Kiranas and mom-and-pop stores across the country. Interestingly, many users using Khatabook apps are first-time internet users, which means they don’t have any previous digital footprints.

Khatabook’s data science team uses the new information it gets from its users every day to understand user behavior, mitigate payment and credit risks, predict adoption and business growth, as well as generating and prioritizing leads.

The company relies on data science to identify the nature of merchant users, whether they are suppliers or retailers, as well as the category of business they operate in, the primary purpose for which they maintain Khatabook, etc. She also uses this to decipher strategy and assess product performance.

When it comes to mitigating risk, Khatabook’s data science team uses advanced artificial intelligence (AI) and machine learning (ML) models to mitigate risk. Data science is also the primary driver of merchant credit underwriting.

Business predictability is another area where Khatabook’s data science team helps make business decisions. “We estimate organic and paid customer growth six months in advance based on the data science framework, taking into account all other external factors, new user acquisition, customer retention aspects. past users, marketing spend and other big variables, ”explained Ravish Naresh, CEO and co-founder of Khatabook.

Currently, KhataBook offers five different products – namely Gold Rate, Payments, Business Tips, GST, Salary – making it a compelling use case for cross-selling and upselling. Cross-selling and upselling is typically done at the middle to late stage of the funnel, when a customer has already indicated they are likely to buy a product or service.

Khatabook uses data science to identify potential users of other apps and identify who will be most likely to purchase the premium plans. “All cross-selling and lead conversion efforts are prioritized using data science models,” Naresh added.

Additionally, he said, at Khatabook they manage risk using a mix of automatic blockers that block suspicious users based on pre-defined rules and an ML model that assigns a risk score to potential users. of fraud.

“Automatic blockers and the ML-based risk model work in tandem to prevent fraud within the Khatabook payments ecosystem. Our CTS (Check Truncation System) and FTS (Sales Fraud) numbers have remained healthy and well below industry thresholds, ”Naresh said.

Extension mode: ON

The team told Analytics India Magazine that they are currently recruiting for a variety of data science positions, including Director of Data Science, Associate Director of Analytics, Management Analytics and Scientist. main data. The company is looking for candidates with between three and eight years of experience.

Khatabook recruits data science and machine learning professionals to meet three key objectives:

  • Identification of merchant authenticity for fraud and loan risk
  • Predict business performance and plan accordingly
  • Customize the product and create AI products to reduce the effort

Team structure

At Khatabook, the data science and analysis team is made up of 30 members.

Analytics and data science is a centralized function in Khatabook. For example, Khatabook offers five products, and each product has a data science manager and a team of 4-5 data analysts / scientists.

Interview process

Khatabook’s data science feature has two components: business analytics and machine learning.

So the interview process for business analysis would include –

  • Selection round (technical analysis + business case study) – Knockout round
  • Another round of technical analysis
  • Analytical case study
  • Business head circumference
  • Cultural assembly tour

For machine learning, the interview process would include:

  • Scouting round (previous projects + ML concepts) – Knockout round
  • Technical analysis cycle – machine learning
  • Business case study tour
  • ML technical mission (practical coding)
  • Cultural assembly tour

Are you cut out for this job?

Here are some of the prerequisites for applying for data science and machine learning jobs at Khatabook.

  • Knowledge of various machine learning techniques (clustering, time series, decision tree learning, fraud / anomaly detection, recommendation algorithm, etc.)
  • Knowledge of advanced statistical techniques and concepts such as regression, statistical testing and appropriate use, properties of distributions, etc., and experience with applications
  • Excellent communication skills (both written and verbal) for coordination between teams
  • A willingness to learn and master new technologies and techniques

Skills

Some of the skills required to work at Khatabook include

  • Technical skills: Proficiency in SQL, Excel, other scripting languages ​​(Python, R, etc.)
  • Solid experience working with BI tools (Tableau, Power BI, etc.)

Data science tools

Khatabook uses tools like Git, Airflow, Tensorflow, Keras, MLOps, Mix panel, Snowflake, Tableau, etc.

See also
Ather Energy Data Science Hiring Process

Expectations

According to Khatabook, the ideal candidate must demonstrate four main abilities:

  • Good business acumen and structured problem solving skills
  • Sense of irreproachable product
  • Technical expertise in machine learning / analytical techniques
  • Strong sense of belonging

In addition to these, some of the other metrics (KRA and KPA) used to assess candidates for the Khatabook data science team include

  • Understand the business applications behind ML / analytics techniques
  • A solid foundation of ML statistics or algorithms applicable to roles
  • Bias for action; focus on the business value generated by the information
  • Write clean, optimized production ready code

Dos and Don’ts

Naresh said most applicants who apply for data science jobs at Khatabook tend to give more weight to explaining the models rather than understanding the problem. Additionally, he said they don’t emphasize presentation skills or are less articulate when explaining the task. “Some of them have extensive knowledge but lack depth. It’s better to know only two techniques, but to know them in depth, ”added Naresh.

Work culture

Naresh said they have a smaller team with higher responsibilities. The team is also horizontal and serves all functions of the company where the opportunities exist. This gives the team the freedom to work in all areas and to solve a variety of problems.

“In addition to the incredible range of work, we believe in ownership and interpersonal learning. Team members are free to design their own workflow aligning them with the big goal, ”said Naresh. “We very much encourage interpersonal learning and brainstorming with our peers because we understand that we face very unique problems and that different perspectives will help us achieve better results. “

What can you expect from Khatabook?

Khatabook is in the tech business for emerging markets. Many users do not have a previous digital fingerprint. As digital adoption increases, more new data is being generated, giving the team a fantastic opportunity to work on exciting use cases and solve problems. In addition, user behavior in emerging markets is changing rapidly. This makes Khatabook an exciting place to work for any data science professional.

On top of that, Khatabook offers a plethora of workplace benefits to employees, such as unlimited time off, extended paternity leave, week-long company-wide mental health breaks at regular intervals. , no Wednesday meeting, referral bonuses, internet and home office expense reports. , virtual team parties, vaccination campaigns for employees and cultural virtual team events resulting in a strong work culture and a collaborative team environment.

Are you ready?

Finally, here are some of the key things to keep in mind when applying for data science positions at Khatabook –

  • Be prepared to meet the business value of your work
  • Freshen up the concepts behind machine learning techniques you are familiar with and also understand their broader business applications
  • Learn to work with unstructured problems; solve case studies
  • Have a good idea of ​​data engineering concepts to implement models in production

So what are you waiting for? Click on here to apply for data science jobs at Khatabook today!


Join our Telegram Group. Be part of an engaging community



Share.

Comments are closed.