Data Science & AI consultancy
Data Science Consultancy
We provide AI consulting on a client's challenge, proposing the most optimal solution with a detailed roadmap and time estimates. We are visioners, so not only do we solve your issues but we also build up upon and improve them. Our specialization is the most peculiar fields and solution this is why we tackle your problems.
MVP Solutions Development
Leveraging our diverse team, we create MVPs for our clients' challenges. Moreover, our approach will bring you the most optimal and reliable solution with the outline of all possible future developments. We are professionals, so you should expect your MVP in 8-14 weeks
Focus
Recommended Providers
Portfolio
Clothes detection
Tech Challenge
- Accurately detecting clothes on users photos
- High loads system that gives response for thousands of users in one time
- Easy-to-deploy solution
Technologies
- Python
- TensorFlow
- React
- Computer Vision
- Neural Networks
- AWS
- REST
- aiohttp
- Visual Search
Solution
- Detection and recognition of garments and accessories.
- Style analysis including colours, shapes, and even fabric.
- Clothes recommendation based on both user-specified preferences and most fitting to a user's style features.
App for meetings
Technologies
- Python
- Django
- Django Rest framework
- Recommendation System,
- Sklearn
- XGBoost
- Pandas
- LambdaRank
- TensorFlow
- Computer Vision
- NLP
Tech Challenge
- Create engaging level system that gradually increases in complexity and reward
- Create a recommendation system that connect people by interest
- Comprehensive user clustering by location and interests
- Deep analysis of new activities a user might find interesting for broadening their horizon by creating correlation matrices
Solution
- Use the technologies that support fast start and can easily become more sophisticated as the project grows.
- Create a fast solution for resolving conflicts and introducing contracts between front-end and back-end.
- Design level system, so that it would be easy to start, but that didn't lost engagement in a later period of time
Scoring system
Summary
We provided an end-to-end outsource of credit scoring system for Romania and created the REST API for the new scoring system. As a result, our solution showed the best AUC score among the other contractors contacted by the company.
Technologies
- Python
- Machine Learning
- Mathematical Modelling
- REST
Tech Challenge
- Scoring with fast response users in real times
- Best solution AUC between all other contractors
- Easy-to-deploy solution
Casino Roulette Recognition
Summary
However improbable this might seem, even such business as casinos tries to make their every customer comfortable and happy, even though sometimes people are in special needs. This is why our client needed:
- Recognition of ball placement on a roulette wheel.
- A feature of smart casino tables for people with impaired sight and hearing.
- Device built-in solution with real-time performance and high sensitivity to mistakes.
Social network analysis
We provided an analysis of the EULAR conference with presentation of numerous pharmaceutical companies' solutions and activities. On the base of analysis, made the topic-modeling of social media activities.
The data was processed with use of the natural language processing and Python.
Technologies
- Topic-modelling
- Python
- Natural language processing
Tech Challenge
- Analyse 10 000+ of tweets
- Prepare a visual understandable squeez of information in the last changes in the field
Face recognition system for retail
As demand grows, retail shops struggle to create the best customer service, since seldom do they completely understand a regular person's needs. This is why our solution provides:
- Insight into the customer opinion of the provided service through emotion recognition.
- Security for customers and workers through criminal detection based on a provided database of dangerous individuals with the ability to manually update it.
- Comprehensive customer analysis including gender and age.
- FaceID-like system for keeping track of regular customers.
Reviews
the project
Custom Solution Development for Software Development Company
"They were a team of great communicators - they give fast responses, even at non-working hours."
the reviewer
the review
The client submitted this review online.
Please describe your company and your position there.
I am the CEO of RSOFT GROUP which is a software development service company based in Poland with offices in Poland and in Czech Republic. We deliver Software Development outsourcing services to international clients and we work on projects end-to-end starting from requirements gathering, design, implementation, deployment and testing.
For what projects/services did your company hire Postdata, and what were your goals?
We were in need of Data Science professionals with a startup mindset ready to ideate and test a solution without supervision. Take a lead in developing a solution. Postdata develop, test and ship ready to use solutions.
How did you select this vendor and what were the deciding factors?
Based on recommendations and positive reviews. Postdata team have experienced Data Science researchers who completed successful projects in various domains from Fintech to Computer Vision. The portfolio works proves that they know what they are talking about.
Describe the scope of work in detail, including the project steps, key deliverables, and technologies used.
A system meant for managing fish, shrimp and oysters production data required additional modules for the data analysis. The Data Science work required included a number of classification problems, choosing the best candidates for mating in maritime agriculture production, as well as regression analysis including phenotype and genetic data. There was a number of Machine Learning algorithms implemented and tested to satisfy the business requirements, and the Data Science work has been finally accomplished with the usage of Deep Learning methods.
How many people from the vendor's team worked with you, and what were their positions?
There were three people involved. Andrey Rohovy as a project coordinator and data scientist. Oleksii Piddiachyi - data scientist focused on research. Pavel Filatov - full-stack developer.
Can you share any measurable outcomes of the project or general feedback about the deliverables?
The delivered Deep Learning solution has fullfilled needs of our client with the expected classificaton and prediction accuracy measured by a number of statistical measures. The solution has allowed our client for a better effectiveness in the agricultural production, as well as mating process chosing the right animals for further mating, growth, and production.
Describe their project management style, including communication tools and timeliness.
Postdata was very agile in managing the project, listening to the requirements, and delivering on time. They were a team of great communicators - they give fast responses, even at non-working hours.
What did you find most impressive or unique about this company?
The communication and the quality of the work they have delivered to us given limited time.
Are there any areas for improvement or something they could have done differently?
I cannot think of anything.
Postdata has fulfilled the client's needs with the expected classifications and prediction accuracy. They were agile in managing the project, maintaining a timely workflow, fast responses, and availability outside working hours. In the end, the client found no need for improvement.